├── Chapter02 ├── .ipynb_checkpoints │ ├── 2.09 Building a Video Game Bot -checkpoint.ipynb │ ├── 2.1 Basic Simulations-checkpoint.ipynb │ ├── 2.10 TensorFlow Fundamentals-checkpoint.ipynb │ ├── 2.11 TensorBoard-checkpoint.ipynb │ ├── 2.2 Training an agent to Walk-checkpoint.ipynb │ ├── 2.7 Basic Simulations-checkpoint.ipynb │ ├── 2.8 Training an Robot to Walk-checkpoint.ipynb │ ├── 2.9 Building a Video Game Bot -checkpoint.ipynb │ ├── TensorBoard-checkpoint.ipynb │ ├── TensorFlow Basics-checkpoint.ipynb │ └── Video Game Bot using OpenAI Universe-checkpoint.ipynb ├── 2.07 Basic Simulations.ipynb ├── 2.08 Training an Robot to Walk.ipynb ├── 2.09 Building a Video Game Bot .ipynb ├── 2.10 TensorFlow Fundamentals.ipynb ├── 2.11 TensorBoard.ipynb └── logs │ └── events.out.tfevents.1527762800.sudharsan ├── Chapter03 ├── .ipynb_checkpoints │ ├── 3.1 Value Iteration - Frozen Lake Problem-checkpoint.ipynb │ ├── 3.12 Value Iteration - Frozen Lake Problem-checkpoint.ipynb │ ├── 3.13 Policy Iteration - Frozen Lake Problem-checkpoint.ipynb │ └── 3.2 Policy Iteration - Frozen Lake Problem-checkpoint.ipynb ├── 3.12 Value Iteration - Frozen Lake Problem.ipynb ├── 3.13 Policy Iteration - Frozen Lake Problem.ipynb └── images │ └── B09792_03_50.png ├── Chapter04 ├── .ipynb_checkpoints │ ├── 4.1 Estimating Value of Pi using Monte Carlo-checkpoint.ipynb │ ├── 4.2 BlackJack with First visit MC-checkpoint.ipynb │ ├── 4.2 Estimating Value of Pi using Monte Carlo-checkpoint.ipynb │ └── 4.6 BlackJack with First visit MC-checkpoint.ipynb ├── 4.2 Estimating Value of Pi using Monte Carlo.ipynb └── 4.6 BlackJack with First visit MC.ipynb ├── Chapter05 ├── .ipynb_checkpoints │ ├── 5.5 Taxi Problem - Q Learning-checkpoint.ipynb │ └── 5.7 Taxi Problem - SARSA-checkpoint.ipynb ├── 5.5 Taxi Problem - Q Learning.ipynb └── 5.7 Taxi Problem - SARSA.ipynb ├── Chapter06 ├── .ipynb_checkpoints │ ├── 6.1 MAB - Various Exploration Strategies-checkpoint.ipynb │ └── 6.7 Identifying Right AD Banner Using MAB-checkpoint.ipynb ├── 6.1 MAB - Various Exploration Strategies.ipynb ├── 6.7 Identifying Right AD Banner Using MAB.ipynb └── images │ └── B09792_06_01.png ├── Chapter07 ├── MUJOCO_LOG.TXT ├── config.py ├── demo │ ├── __init__.py │ ├── game.py │ ├── object.py │ ├── robot.py │ └── utils.py ├── distribution │ ├── __init__.py │ ├── categorical.py │ └── diagonal_gaussian.py ├── environment.py ├── eval.py ├── game.py ├── krylov.py ├── layer.py ├── layers.py ├── log │ ├── Acrobot │ │ ├── checkpoint │ │ └── events.out.tfevents.1506500394.ywz-WorkStation-T7400 │ ├── CartPole │ │ ├── checkpoint │ │ └── events.out.tfevents.1506667268.ywz-WorkStation-T7400 │ ├── HalfCheetah │ │ ├── checkpoint │ │ └── events.out.tfevents.1506338471.ywz-WorkStation-T7400 │ ├── Hopper │ │ ├── checkpoint │ │ └── events.out.tfevents.1506658875.ywz-WorkStation-T7400 │ ├── Pendulum │ │ ├── checkpoint │ │ └── events.out.tfevents.1506666537.ywz-WorkStation-T7400 │ ├── Reacher │ │ ├── checkpoint │ │ └── events.out.tfevents.1506398906.ywz-WorkStation-T7400 │ ├── Swimmer │ │ ├── checkpoint │ │ └── events.out.tfevents.1526197305.ywz-PC │ └── Walker2d │ │ ├── checkpoint │ │ └── events.out.tfevents.1506671852.ywz-WorkStation-T7400 ├── logger.py ├── main.py ├── mlp.py ├── optimizer.py ├── parallel.py ├── policy │ ├── __init__.py │ ├── categorical_mlp.py │ ├── deterministic_mlp.py │ └── gaussian_mlp.py ├── ppo.py ├── q_learning.py ├── q_network.py ├── replay_memory.py ├── sampler.py ├── simulator.py ├── test.py ├── train.py ├── trpo.py ├── utils.py └── value │ ├── __init__.py │ ├── linear_fitting.py │ └── mlp_fitting.py ├── Chapter08 ├── .ipynb_checkpoints │ └── 8.8 Building an Agent to Play Atari Games-checkpoint.ipynb ├── 8.8 Building an Agent to Play Atari Games.ipynb └── logs │ ├── events.out.tfevents.1526989751.sudharsan │ ├── events.out.tfevents.1526990072.sudharsan │ └── events.out.tfevents.1528714237.sudharsan ├── Chapter09 ├── .ipynb_checkpoints │ ├── 9.4 Basic Doom Game-checkpoint.ipynb │ └── 9.5 Doom Game Using DRQN-checkpoint.ipynb ├── 9.4 Basic Doom Game.ipynb ├── 9.5 Doom Game Using DRQN.ipynb ├── basic.cfg ├── basic.wad ├── deathmatch.cfg └── deathmatch.wad ├── Chapter10 ├── .ipynb_checkpoints │ └── 10.5 Drive up the Mountain Using A3C-checkpoint.ipynb ├── 10.5 Drive up the Mountain Using A3C.ipynb └── logs │ └── events.out.tfevents.1528713441.sudharsan ├── Chapter11 ├── .ipynb_checkpoints │ ├── 11.2 Lunar Lander Using Policy Gradients-checkpoint.ipynb │ └── 11.3 Swinging Up the Pendulum Using DDPG-checkpoint.ipynb ├── 11.2 Lunar Lander Using Policy Gradients.ipynb ├── 11.3 Swinging Up the Pendulum Using DDPG.ipynb └── logs │ └── events.out.tfevents.1528712442.sudharsan ├── Chapter12 ├── __init__.py ├── algorithmic_03.py ├── atari_02.py ├── box2d_04.py ├── cartpole.py ├── classic_control_05.py ├── mujoco_06.py ├── robotics_07.py ├── start1.py └── toy_text_08.py ├── Chapter13 ├── actor_critic_net.py ├── actor_network.py ├── config.py ├── critic_network.py ├── dpg.py ├── eval.py ├── layers.py ├── log │ ├── Acrobot-v1 │ │ ├── checkpoint │ │ └── train │ │ │ └── events.out.tfevents.1523886598.ywz-PC │ ├── CartPole-v0 │ │ ├── checkpoint │ │ └── train │ │ │ └── events.out.tfevents.1525870448.ywz-PC │ ├── MountainCar-v0 │ │ ├── checkpoint │ │ └── train │ │ │ └── events.out.tfevents.1526196635.ywz-PC │ └── Pendulum-v0 │ │ ├── checkpoint │ │ └── train │ │ └── events.out.tfevents.1525871560.ywz-PC ├── main.py ├── optimizer.py ├── replay_memory.py ├── task.py └── train.py ├── Chapter14 ├── a3c.py ├── cluster.py ├── demo │ ├── __init__.py │ ├── game.py │ ├── object.py │ ├── robot.py │ └── utils.py ├── doom │ ├── _vizdoom.ini │ ├── doom.py │ ├── game.py │ └── scenarios │ │ ├── basic.cfg │ │ ├── basic.wad │ │ ├── cig.cfg │ │ ├── cig.wad │ │ ├── cig_with_unknown.wad │ │ ├── deadly_corridor.cfg │ │ ├── deadly_corridor.wad │ │ ├── deathmatch.cfg │ │ ├── deathmatch.wad │ │ ├── defend_the_center.cfg │ │ ├── defend_the_center.wad │ │ ├── defend_the_line.cfg │ │ ├── defend_the_line.wad │ │ ├── health_gathering.cfg │ │ ├── health_gathering.wad │ │ ├── health_gathering_supreme.wad │ │ ├── learning.cfg │ │ ├── multi.cfg │ │ ├── multi_deathmatch.wad │ │ ├── multi_duel.cfg │ │ ├── multi_duel.wad │ │ ├── my_way_home.cfg │ │ ├── my_way_home.wad │ │ ├── predict_position.cfg │ │ ├── predict_position.wad │ │ ├── rocket_basic.cfg │ │ ├── rocket_basic.wad │ │ ├── simpler_basic.cfg │ │ ├── simpler_basic.wad │ │ ├── take_cover.cfg │ │ └── take_cover.wad ├── environment.py ├── ff_policy.py ├── game.py ├── helper │ └── tmux ├── layer.py ├── lstm_policy.py ├── minecraft │ ├── __init__.py │ └── game.py ├── parameter.py ├── save │ ├── breakout │ │ └── train │ │ │ ├── log_0 │ │ │ └── events.out.tfevents.1532007719.ywz-PC │ │ │ └── log_1 │ │ │ └── events.out.tfevents.1532007719.ywz-PC │ ├── demo │ │ └── train │ │ │ ├── checkpoint │ │ │ ├── log_0 │ │ │ └── events.out.tfevents.1532007504.ywz-PC │ │ │ └── log_1 │ │ │ └── events.out.tfevents.1532007504.ywz-PC │ └── minecraftbasic-v0 │ │ └── train │ │ └── log_0 │ │ └── events.out.tfevents.1532007895.ywz-PC ├── test.py ├── timer.py ├── train.py ├── utils.py └── worker.py ├── Chapter15 ├── __init__.py ├── commands.txt └── src │ ├── __init__.py │ ├── alphagozero_agent.py │ ├── config.py │ ├── constants.py │ ├── controller.py │ ├── features.py │ ├── go.py │ ├── mcts.py │ ├── network.py │ ├── preprocessing.py │ ├── train.py │ └── utils.py ├── Chapter16 ├── RL chatbot.ipynb ├── convert_checkpoint.py ├── data_parser.py ├── data_reader.py ├── feature_extracter.py ├── model │ ├── Reversed │ │ └── checkpoint │ └── model-56-3000 │ │ └── checkpoint ├── pg_model.py ├── results │ ├── sample_input.txt │ └── sample_output_RL.txt ├── seq_model.py ├── test.py └── train.py ├── Chapter17 ├── README.md ├── __init__.py └── src │ ├── __init__.py │ ├── child_network.py │ ├── cifar10_processor.py │ ├── config.py │ ├── constants.py │ ├── controller.py │ └── train.py ├── Chapter18 ├── actor.py ├── agent.py ├── critic.py ├── helper.py └── train.py ├── Chapter19 ├── .ipynb_checkpoints │ ├── 13.3 Deep Q Learning From Demonstrations-checkpoint.ipynb │ └── 13.4 Hindsight Experience Replay-checkpoint.ipynb ├── 13.3 Deep Q Learning From Demonstrations.ipynb ├── 13.4 Hindsight Experience Replay.ipynb └── images │ ├── B09792_13_01.png │ └── B09792_13_02.png ├── LICENSE └── README.md /Chapter02/.ipynb_checkpoints/2.09 Building a Video Game Bot -checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter02/.ipynb_checkpoints/2.09 Building a Video Game Bot -checkpoint.ipynb -------------------------------------------------------------------------------- /Chapter02/.ipynb_checkpoints/2.1 Basic Simulations-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter02/.ipynb_checkpoints/2.1 Basic Simulations-checkpoint.ipynb -------------------------------------------------------------------------------- /Chapter02/.ipynb_checkpoints/2.10 TensorFlow Fundamentals-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter02/.ipynb_checkpoints/2.10 TensorFlow Fundamentals-checkpoint.ipynb -------------------------------------------------------------------------------- /Chapter02/.ipynb_checkpoints/2.11 TensorBoard-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter02/.ipynb_checkpoints/2.11 TensorBoard-checkpoint.ipynb -------------------------------------------------------------------------------- /Chapter02/.ipynb_checkpoints/2.2 Training an agent to Walk-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter02/.ipynb_checkpoints/2.2 Training an agent to Walk-checkpoint.ipynb -------------------------------------------------------------------------------- /Chapter02/.ipynb_checkpoints/2.7 Basic Simulations-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter02/.ipynb_checkpoints/2.7 Basic Simulations-checkpoint.ipynb -------------------------------------------------------------------------------- /Chapter02/.ipynb_checkpoints/2.8 Training an Robot to Walk-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter02/.ipynb_checkpoints/2.8 Training an Robot to Walk-checkpoint.ipynb -------------------------------------------------------------------------------- /Chapter02/.ipynb_checkpoints/2.9 Building a Video Game Bot -checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter02/.ipynb_checkpoints/2.9 Building a Video Game Bot -checkpoint.ipynb -------------------------------------------------------------------------------- /Chapter02/.ipynb_checkpoints/TensorBoard-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter02/.ipynb_checkpoints/TensorBoard-checkpoint.ipynb -------------------------------------------------------------------------------- /Chapter02/.ipynb_checkpoints/TensorFlow Basics-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter02/.ipynb_checkpoints/TensorFlow Basics-checkpoint.ipynb -------------------------------------------------------------------------------- /Chapter02/.ipynb_checkpoints/Video Game Bot using OpenAI Universe-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter02/.ipynb_checkpoints/Video Game Bot using OpenAI Universe-checkpoint.ipynb -------------------------------------------------------------------------------- /Chapter02/2.07 Basic Simulations.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter02/2.07 Basic Simulations.ipynb -------------------------------------------------------------------------------- /Chapter02/2.08 Training an Robot to Walk.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter02/2.08 Training an Robot to Walk.ipynb -------------------------------------------------------------------------------- /Chapter02/2.09 Building a Video Game Bot .ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter02/2.09 Building a Video Game Bot .ipynb -------------------------------------------------------------------------------- /Chapter02/2.10 TensorFlow Fundamentals.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter02/2.10 TensorFlow Fundamentals.ipynb -------------------------------------------------------------------------------- /Chapter02/2.11 TensorBoard.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter02/2.11 TensorBoard.ipynb -------------------------------------------------------------------------------- /Chapter02/logs/events.out.tfevents.1527762800.sudharsan: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter02/logs/events.out.tfevents.1527762800.sudharsan -------------------------------------------------------------------------------- /Chapter03/.ipynb_checkpoints/3.1 Value Iteration - Frozen Lake Problem-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter03/.ipynb_checkpoints/3.1 Value Iteration - Frozen Lake Problem-checkpoint.ipynb -------------------------------------------------------------------------------- /Chapter03/.ipynb_checkpoints/3.12 Value Iteration - Frozen Lake Problem-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter03/.ipynb_checkpoints/3.12 Value Iteration - Frozen Lake Problem-checkpoint.ipynb -------------------------------------------------------------------------------- /Chapter03/.ipynb_checkpoints/3.13 Policy Iteration - Frozen Lake Problem-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter03/.ipynb_checkpoints/3.13 Policy Iteration - Frozen Lake Problem-checkpoint.ipynb -------------------------------------------------------------------------------- /Chapter03/.ipynb_checkpoints/3.2 Policy Iteration - Frozen Lake Problem-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter03/.ipynb_checkpoints/3.2 Policy Iteration - Frozen Lake Problem-checkpoint.ipynb -------------------------------------------------------------------------------- /Chapter03/3.12 Value Iteration - Frozen Lake Problem.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter03/3.12 Value Iteration - Frozen Lake Problem.ipynb -------------------------------------------------------------------------------- /Chapter03/3.13 Policy Iteration - Frozen Lake Problem.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter03/3.13 Policy Iteration - Frozen Lake Problem.ipynb -------------------------------------------------------------------------------- /Chapter03/images/B09792_03_50.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter03/images/B09792_03_50.png -------------------------------------------------------------------------------- /Chapter04/.ipynb_checkpoints/4.1 Estimating Value of Pi using Monte Carlo-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter04/.ipynb_checkpoints/4.1 Estimating Value of Pi using Monte Carlo-checkpoint.ipynb -------------------------------------------------------------------------------- /Chapter04/.ipynb_checkpoints/4.2 BlackJack with First visit MC-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter04/.ipynb_checkpoints/4.2 BlackJack with First visit MC-checkpoint.ipynb -------------------------------------------------------------------------------- /Chapter04/.ipynb_checkpoints/4.2 Estimating Value of Pi using Monte Carlo-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter04/.ipynb_checkpoints/4.2 Estimating Value of Pi using Monte Carlo-checkpoint.ipynb -------------------------------------------------------------------------------- /Chapter04/.ipynb_checkpoints/4.6 BlackJack with First visit MC-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter04/.ipynb_checkpoints/4.6 BlackJack with First visit MC-checkpoint.ipynb -------------------------------------------------------------------------------- /Chapter04/4.2 Estimating Value of Pi using Monte Carlo.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter04/4.2 Estimating Value of Pi using Monte Carlo.ipynb -------------------------------------------------------------------------------- /Chapter04/4.6 BlackJack with First visit MC.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter04/4.6 BlackJack with First visit MC.ipynb -------------------------------------------------------------------------------- /Chapter05/.ipynb_checkpoints/5.5 Taxi Problem - Q Learning-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter05/.ipynb_checkpoints/5.5 Taxi Problem - Q Learning-checkpoint.ipynb -------------------------------------------------------------------------------- /Chapter05/.ipynb_checkpoints/5.7 Taxi Problem - SARSA-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter05/.ipynb_checkpoints/5.7 Taxi Problem - SARSA-checkpoint.ipynb -------------------------------------------------------------------------------- /Chapter05/5.5 Taxi Problem - Q Learning.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter05/5.5 Taxi Problem - Q Learning.ipynb -------------------------------------------------------------------------------- /Chapter05/5.7 Taxi Problem - SARSA.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter05/5.7 Taxi Problem - SARSA.ipynb -------------------------------------------------------------------------------- /Chapter06/.ipynb_checkpoints/6.1 MAB - Various Exploration Strategies-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter06/.ipynb_checkpoints/6.1 MAB - Various Exploration Strategies-checkpoint.ipynb -------------------------------------------------------------------------------- /Chapter06/.ipynb_checkpoints/6.7 Identifying Right AD Banner Using MAB-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter06/.ipynb_checkpoints/6.7 Identifying Right AD Banner Using MAB-checkpoint.ipynb -------------------------------------------------------------------------------- /Chapter06/6.1 MAB - Various Exploration Strategies.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter06/6.1 MAB - Various Exploration Strategies.ipynb -------------------------------------------------------------------------------- /Chapter06/6.7 Identifying Right AD Banner Using MAB.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter06/6.7 Identifying Right AD Banner Using MAB.ipynb -------------------------------------------------------------------------------- /Chapter06/images/B09792_06_01.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter06/images/B09792_06_01.png -------------------------------------------------------------------------------- /Chapter07/MUJOCO_LOG.TXT: -------------------------------------------------------------------------------- 1 | Sun May 13 16:29:23 2018 2 | ERROR: GLEW initalization error: Missing GL version 3 | 4 | -------------------------------------------------------------------------------- /Chapter07/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter07/config.py -------------------------------------------------------------------------------- /Chapter07/demo/__init__.py: -------------------------------------------------------------------------------- 1 | ''' 2 | Created on Nov 10, 2016 3 | 4 | @author: a0096049 5 | ''' 6 | -------------------------------------------------------------------------------- /Chapter07/demo/game.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter07/demo/game.py -------------------------------------------------------------------------------- /Chapter07/demo/object.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter07/demo/object.py -------------------------------------------------------------------------------- /Chapter07/demo/robot.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter07/demo/robot.py -------------------------------------------------------------------------------- /Chapter07/demo/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter07/demo/utils.py -------------------------------------------------------------------------------- /Chapter07/distribution/__init__.py: -------------------------------------------------------------------------------- 1 | ''' 2 | Created on 18 Sep 2017 3 | 4 | @author: ywz 5 | ''' 6 | -------------------------------------------------------------------------------- /Chapter07/distribution/categorical.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter07/distribution/categorical.py -------------------------------------------------------------------------------- /Chapter07/distribution/diagonal_gaussian.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter07/distribution/diagonal_gaussian.py -------------------------------------------------------------------------------- /Chapter07/environment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter07/environment.py -------------------------------------------------------------------------------- /Chapter07/eval.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter07/eval.py -------------------------------------------------------------------------------- /Chapter07/game.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter07/game.py -------------------------------------------------------------------------------- /Chapter07/krylov.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter07/krylov.py -------------------------------------------------------------------------------- /Chapter07/layer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter07/layer.py -------------------------------------------------------------------------------- /Chapter07/layers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter07/layers.py -------------------------------------------------------------------------------- /Chapter07/log/Acrobot/checkpoint: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter07/log/Acrobot/checkpoint -------------------------------------------------------------------------------- /Chapter07/log/Acrobot/events.out.tfevents.1506500394.ywz-WorkStation-T7400: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter07/log/Acrobot/events.out.tfevents.1506500394.ywz-WorkStation-T7400 -------------------------------------------------------------------------------- /Chapter07/log/CartPole/checkpoint: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter07/log/CartPole/checkpoint -------------------------------------------------------------------------------- /Chapter07/log/CartPole/events.out.tfevents.1506667268.ywz-WorkStation-T7400: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter07/log/CartPole/events.out.tfevents.1506667268.ywz-WorkStation-T7400 -------------------------------------------------------------------------------- /Chapter07/log/HalfCheetah/checkpoint: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter07/log/HalfCheetah/checkpoint -------------------------------------------------------------------------------- /Chapter07/log/HalfCheetah/events.out.tfevents.1506338471.ywz-WorkStation-T7400: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter07/log/HalfCheetah/events.out.tfevents.1506338471.ywz-WorkStation-T7400 -------------------------------------------------------------------------------- /Chapter07/log/Hopper/checkpoint: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter07/log/Hopper/checkpoint -------------------------------------------------------------------------------- /Chapter07/log/Hopper/events.out.tfevents.1506658875.ywz-WorkStation-T7400: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter07/log/Hopper/events.out.tfevents.1506658875.ywz-WorkStation-T7400 -------------------------------------------------------------------------------- /Chapter07/log/Pendulum/checkpoint: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter07/log/Pendulum/checkpoint -------------------------------------------------------------------------------- /Chapter07/log/Pendulum/events.out.tfevents.1506666537.ywz-WorkStation-T7400: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter07/log/Pendulum/events.out.tfevents.1506666537.ywz-WorkStation-T7400 -------------------------------------------------------------------------------- /Chapter07/log/Reacher/checkpoint: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter07/log/Reacher/checkpoint -------------------------------------------------------------------------------- /Chapter07/log/Reacher/events.out.tfevents.1506398906.ywz-WorkStation-T7400: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter07/log/Reacher/events.out.tfevents.1506398906.ywz-WorkStation-T7400 -------------------------------------------------------------------------------- /Chapter07/log/Swimmer/checkpoint: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter07/log/Swimmer/checkpoint -------------------------------------------------------------------------------- /Chapter07/log/Swimmer/events.out.tfevents.1526197305.ywz-PC: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter07/log/Swimmer/events.out.tfevents.1526197305.ywz-PC -------------------------------------------------------------------------------- /Chapter07/log/Walker2d/checkpoint: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter07/log/Walker2d/checkpoint -------------------------------------------------------------------------------- /Chapter07/log/Walker2d/events.out.tfevents.1506671852.ywz-WorkStation-T7400: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter07/log/Walker2d/events.out.tfevents.1506671852.ywz-WorkStation-T7400 -------------------------------------------------------------------------------- /Chapter07/logger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter07/logger.py -------------------------------------------------------------------------------- /Chapter07/main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter07/main.py -------------------------------------------------------------------------------- /Chapter07/mlp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter07/mlp.py -------------------------------------------------------------------------------- /Chapter07/optimizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter07/optimizer.py -------------------------------------------------------------------------------- /Chapter07/parallel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter07/parallel.py -------------------------------------------------------------------------------- /Chapter07/policy/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /Chapter07/policy/categorical_mlp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter07/policy/categorical_mlp.py -------------------------------------------------------------------------------- /Chapter07/policy/deterministic_mlp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter07/policy/deterministic_mlp.py -------------------------------------------------------------------------------- /Chapter07/policy/gaussian_mlp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter07/policy/gaussian_mlp.py -------------------------------------------------------------------------------- /Chapter07/ppo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter07/ppo.py -------------------------------------------------------------------------------- /Chapter07/q_learning.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter07/q_learning.py -------------------------------------------------------------------------------- /Chapter07/q_network.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter07/q_network.py -------------------------------------------------------------------------------- /Chapter07/replay_memory.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter07/replay_memory.py -------------------------------------------------------------------------------- /Chapter07/sampler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter07/sampler.py -------------------------------------------------------------------------------- /Chapter07/simulator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter07/simulator.py -------------------------------------------------------------------------------- /Chapter07/test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter07/test.py -------------------------------------------------------------------------------- /Chapter07/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter07/train.py -------------------------------------------------------------------------------- /Chapter07/trpo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter07/trpo.py -------------------------------------------------------------------------------- /Chapter07/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter07/utils.py -------------------------------------------------------------------------------- /Chapter07/value/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter07/value/__init__.py -------------------------------------------------------------------------------- /Chapter07/value/linear_fitting.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter07/value/linear_fitting.py -------------------------------------------------------------------------------- /Chapter07/value/mlp_fitting.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter07/value/mlp_fitting.py -------------------------------------------------------------------------------- /Chapter08/.ipynb_checkpoints/8.8 Building an Agent to Play Atari Games-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter08/.ipynb_checkpoints/8.8 Building an Agent to Play Atari Games-checkpoint.ipynb -------------------------------------------------------------------------------- /Chapter08/8.8 Building an Agent to Play Atari Games.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter08/8.8 Building an Agent to Play Atari Games.ipynb -------------------------------------------------------------------------------- /Chapter08/logs/events.out.tfevents.1526989751.sudharsan: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter08/logs/events.out.tfevents.1526989751.sudharsan -------------------------------------------------------------------------------- /Chapter08/logs/events.out.tfevents.1526990072.sudharsan: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter08/logs/events.out.tfevents.1526990072.sudharsan -------------------------------------------------------------------------------- /Chapter08/logs/events.out.tfevents.1528714237.sudharsan: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter08/logs/events.out.tfevents.1528714237.sudharsan -------------------------------------------------------------------------------- /Chapter09/.ipynb_checkpoints/9.4 Basic Doom Game-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter09/.ipynb_checkpoints/9.4 Basic Doom Game-checkpoint.ipynb -------------------------------------------------------------------------------- /Chapter09/.ipynb_checkpoints/9.5 Doom Game Using DRQN-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter09/.ipynb_checkpoints/9.5 Doom Game Using DRQN-checkpoint.ipynb -------------------------------------------------------------------------------- /Chapter09/9.4 Basic Doom Game.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter09/9.4 Basic Doom Game.ipynb -------------------------------------------------------------------------------- /Chapter09/9.5 Doom Game Using DRQN.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter09/9.5 Doom Game Using DRQN.ipynb -------------------------------------------------------------------------------- /Chapter09/basic.cfg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter09/basic.cfg -------------------------------------------------------------------------------- /Chapter09/basic.wad: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter09/basic.wad -------------------------------------------------------------------------------- /Chapter09/deathmatch.cfg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter09/deathmatch.cfg -------------------------------------------------------------------------------- /Chapter09/deathmatch.wad: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter09/deathmatch.wad -------------------------------------------------------------------------------- /Chapter10/.ipynb_checkpoints/10.5 Drive up the Mountain Using A3C-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter10/.ipynb_checkpoints/10.5 Drive up the Mountain Using A3C-checkpoint.ipynb -------------------------------------------------------------------------------- /Chapter10/10.5 Drive up the Mountain Using A3C.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter10/10.5 Drive up the Mountain Using A3C.ipynb -------------------------------------------------------------------------------- /Chapter10/logs/events.out.tfevents.1528713441.sudharsan: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter10/logs/events.out.tfevents.1528713441.sudharsan -------------------------------------------------------------------------------- /Chapter11/.ipynb_checkpoints/11.2 Lunar Lander Using Policy Gradients-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter11/.ipynb_checkpoints/11.2 Lunar Lander Using Policy Gradients-checkpoint.ipynb -------------------------------------------------------------------------------- /Chapter11/.ipynb_checkpoints/11.3 Swinging Up the Pendulum Using DDPG-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter11/.ipynb_checkpoints/11.3 Swinging Up the Pendulum Using DDPG-checkpoint.ipynb -------------------------------------------------------------------------------- /Chapter11/11.2 Lunar Lander Using Policy Gradients.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter11/11.2 Lunar Lander Using Policy Gradients.ipynb -------------------------------------------------------------------------------- /Chapter11/11.3 Swinging Up the Pendulum Using DDPG.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter11/11.3 Swinging Up the Pendulum Using DDPG.ipynb -------------------------------------------------------------------------------- /Chapter11/logs/events.out.tfevents.1528712442.sudharsan: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter11/logs/events.out.tfevents.1528712442.sudharsan -------------------------------------------------------------------------------- /Chapter12/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /Chapter12/algorithmic_03.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter12/algorithmic_03.py -------------------------------------------------------------------------------- /Chapter12/atari_02.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter12/atari_02.py -------------------------------------------------------------------------------- /Chapter12/box2d_04.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter12/box2d_04.py -------------------------------------------------------------------------------- /Chapter12/cartpole.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter12/cartpole.py -------------------------------------------------------------------------------- /Chapter12/classic_control_05.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter12/classic_control_05.py -------------------------------------------------------------------------------- /Chapter12/mujoco_06.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter12/mujoco_06.py -------------------------------------------------------------------------------- /Chapter12/robotics_07.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter12/robotics_07.py -------------------------------------------------------------------------------- /Chapter12/start1.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter12/start1.py -------------------------------------------------------------------------------- /Chapter12/toy_text_08.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter12/toy_text_08.py -------------------------------------------------------------------------------- /Chapter13/actor_critic_net.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter13/actor_critic_net.py -------------------------------------------------------------------------------- /Chapter13/actor_network.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter13/actor_network.py -------------------------------------------------------------------------------- /Chapter13/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter13/config.py -------------------------------------------------------------------------------- /Chapter13/critic_network.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter13/critic_network.py -------------------------------------------------------------------------------- /Chapter13/dpg.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter13/dpg.py -------------------------------------------------------------------------------- /Chapter13/eval.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter13/eval.py -------------------------------------------------------------------------------- /Chapter13/layers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter13/layers.py -------------------------------------------------------------------------------- /Chapter13/log/Acrobot-v1/checkpoint: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter13/log/Acrobot-v1/checkpoint -------------------------------------------------------------------------------- /Chapter13/log/Acrobot-v1/train/events.out.tfevents.1523886598.ywz-PC: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter13/log/Acrobot-v1/train/events.out.tfevents.1523886598.ywz-PC -------------------------------------------------------------------------------- /Chapter13/log/CartPole-v0/checkpoint: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter13/log/CartPole-v0/checkpoint -------------------------------------------------------------------------------- /Chapter13/log/CartPole-v0/train/events.out.tfevents.1525870448.ywz-PC: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter13/log/CartPole-v0/train/events.out.tfevents.1525870448.ywz-PC -------------------------------------------------------------------------------- /Chapter13/log/MountainCar-v0/checkpoint: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter13/log/MountainCar-v0/checkpoint -------------------------------------------------------------------------------- /Chapter13/log/MountainCar-v0/train/events.out.tfevents.1526196635.ywz-PC: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter13/log/MountainCar-v0/train/events.out.tfevents.1526196635.ywz-PC -------------------------------------------------------------------------------- /Chapter13/log/Pendulum-v0/checkpoint: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter13/log/Pendulum-v0/checkpoint -------------------------------------------------------------------------------- /Chapter13/log/Pendulum-v0/train/events.out.tfevents.1525871560.ywz-PC: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter13/log/Pendulum-v0/train/events.out.tfevents.1525871560.ywz-PC -------------------------------------------------------------------------------- /Chapter13/main.py: -------------------------------------------------------------------------------- 1 | ''' 2 | Created on Apr 10, 2018 3 | 4 | @author: ywz 5 | ''' 6 | -------------------------------------------------------------------------------- /Chapter13/optimizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter13/optimizer.py -------------------------------------------------------------------------------- /Chapter13/replay_memory.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter13/replay_memory.py -------------------------------------------------------------------------------- /Chapter13/task.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter13/task.py -------------------------------------------------------------------------------- /Chapter13/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter13/train.py -------------------------------------------------------------------------------- /Chapter14/a3c.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter14/a3c.py -------------------------------------------------------------------------------- /Chapter14/cluster.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter14/cluster.py -------------------------------------------------------------------------------- /Chapter14/demo/__init__.py: -------------------------------------------------------------------------------- 1 | ''' 2 | Created on Nov 10, 2016 3 | 4 | @author: a0096049 5 | ''' 6 | -------------------------------------------------------------------------------- /Chapter14/demo/game.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter14/demo/game.py -------------------------------------------------------------------------------- /Chapter14/demo/object.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter14/demo/object.py -------------------------------------------------------------------------------- /Chapter14/demo/robot.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter14/demo/robot.py -------------------------------------------------------------------------------- /Chapter14/demo/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter14/demo/utils.py -------------------------------------------------------------------------------- /Chapter14/doom/_vizdoom.ini: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter14/doom/_vizdoom.ini -------------------------------------------------------------------------------- /Chapter14/doom/doom.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter14/doom/doom.py -------------------------------------------------------------------------------- /Chapter14/doom/game.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter14/doom/game.py -------------------------------------------------------------------------------- /Chapter14/doom/scenarios/basic.cfg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter14/doom/scenarios/basic.cfg -------------------------------------------------------------------------------- /Chapter14/doom/scenarios/basic.wad: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter14/doom/scenarios/basic.wad -------------------------------------------------------------------------------- /Chapter14/doom/scenarios/cig.cfg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter14/doom/scenarios/cig.cfg -------------------------------------------------------------------------------- /Chapter14/doom/scenarios/cig.wad: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter14/doom/scenarios/cig.wad -------------------------------------------------------------------------------- /Chapter14/doom/scenarios/cig_with_unknown.wad: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter14/doom/scenarios/cig_with_unknown.wad -------------------------------------------------------------------------------- /Chapter14/doom/scenarios/deadly_corridor.cfg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter14/doom/scenarios/deadly_corridor.cfg -------------------------------------------------------------------------------- /Chapter14/doom/scenarios/deadly_corridor.wad: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter14/doom/scenarios/deadly_corridor.wad -------------------------------------------------------------------------------- /Chapter14/doom/scenarios/deathmatch.cfg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter14/doom/scenarios/deathmatch.cfg -------------------------------------------------------------------------------- /Chapter14/doom/scenarios/deathmatch.wad: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter14/doom/scenarios/deathmatch.wad -------------------------------------------------------------------------------- /Chapter14/doom/scenarios/defend_the_center.cfg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter14/doom/scenarios/defend_the_center.cfg -------------------------------------------------------------------------------- /Chapter14/doom/scenarios/defend_the_center.wad: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter14/doom/scenarios/defend_the_center.wad -------------------------------------------------------------------------------- /Chapter14/doom/scenarios/defend_the_line.cfg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter14/doom/scenarios/defend_the_line.cfg -------------------------------------------------------------------------------- /Chapter14/doom/scenarios/defend_the_line.wad: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter14/doom/scenarios/defend_the_line.wad -------------------------------------------------------------------------------- /Chapter14/doom/scenarios/health_gathering.cfg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter14/doom/scenarios/health_gathering.cfg -------------------------------------------------------------------------------- /Chapter14/doom/scenarios/health_gathering.wad: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter14/doom/scenarios/health_gathering.wad -------------------------------------------------------------------------------- /Chapter14/doom/scenarios/health_gathering_supreme.wad: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter14/doom/scenarios/health_gathering_supreme.wad -------------------------------------------------------------------------------- /Chapter14/doom/scenarios/learning.cfg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter14/doom/scenarios/learning.cfg -------------------------------------------------------------------------------- /Chapter14/doom/scenarios/multi.cfg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter14/doom/scenarios/multi.cfg -------------------------------------------------------------------------------- /Chapter14/doom/scenarios/multi_deathmatch.wad: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter14/doom/scenarios/multi_deathmatch.wad -------------------------------------------------------------------------------- /Chapter14/doom/scenarios/multi_duel.cfg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter14/doom/scenarios/multi_duel.cfg -------------------------------------------------------------------------------- /Chapter14/doom/scenarios/multi_duel.wad: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter14/doom/scenarios/multi_duel.wad -------------------------------------------------------------------------------- /Chapter14/doom/scenarios/my_way_home.cfg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter14/doom/scenarios/my_way_home.cfg -------------------------------------------------------------------------------- /Chapter14/doom/scenarios/my_way_home.wad: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter14/doom/scenarios/my_way_home.wad -------------------------------------------------------------------------------- /Chapter14/doom/scenarios/predict_position.cfg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter14/doom/scenarios/predict_position.cfg -------------------------------------------------------------------------------- /Chapter14/doom/scenarios/predict_position.wad: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter14/doom/scenarios/predict_position.wad -------------------------------------------------------------------------------- /Chapter14/doom/scenarios/rocket_basic.cfg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter14/doom/scenarios/rocket_basic.cfg -------------------------------------------------------------------------------- /Chapter14/doom/scenarios/rocket_basic.wad: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter14/doom/scenarios/rocket_basic.wad -------------------------------------------------------------------------------- /Chapter14/doom/scenarios/simpler_basic.cfg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter14/doom/scenarios/simpler_basic.cfg -------------------------------------------------------------------------------- /Chapter14/doom/scenarios/simpler_basic.wad: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter14/doom/scenarios/simpler_basic.wad -------------------------------------------------------------------------------- /Chapter14/doom/scenarios/take_cover.cfg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter14/doom/scenarios/take_cover.cfg -------------------------------------------------------------------------------- /Chapter14/doom/scenarios/take_cover.wad: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter14/doom/scenarios/take_cover.wad -------------------------------------------------------------------------------- /Chapter14/environment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter14/environment.py -------------------------------------------------------------------------------- /Chapter14/ff_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter14/ff_policy.py -------------------------------------------------------------------------------- /Chapter14/game.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter14/game.py -------------------------------------------------------------------------------- /Chapter14/helper/tmux: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter14/helper/tmux -------------------------------------------------------------------------------- /Chapter14/layer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter14/layer.py -------------------------------------------------------------------------------- /Chapter14/lstm_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter14/lstm_policy.py -------------------------------------------------------------------------------- /Chapter14/minecraft/__init__.py: -------------------------------------------------------------------------------- 1 | ''' 2 | Created on Jul 19, 2018 3 | 4 | @author: ywz 5 | ''' 6 | -------------------------------------------------------------------------------- /Chapter14/minecraft/game.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter14/minecraft/game.py -------------------------------------------------------------------------------- /Chapter14/parameter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter14/parameter.py -------------------------------------------------------------------------------- /Chapter14/save/breakout/train/log_0/events.out.tfevents.1532007719.ywz-PC: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter14/save/breakout/train/log_0/events.out.tfevents.1532007719.ywz-PC -------------------------------------------------------------------------------- /Chapter14/save/breakout/train/log_1/events.out.tfevents.1532007719.ywz-PC: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter14/save/breakout/train/log_1/events.out.tfevents.1532007719.ywz-PC -------------------------------------------------------------------------------- /Chapter14/save/demo/train/checkpoint: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter14/save/demo/train/checkpoint -------------------------------------------------------------------------------- /Chapter14/save/demo/train/log_0/events.out.tfevents.1532007504.ywz-PC: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter14/save/demo/train/log_0/events.out.tfevents.1532007504.ywz-PC -------------------------------------------------------------------------------- /Chapter14/save/demo/train/log_1/events.out.tfevents.1532007504.ywz-PC: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter14/save/demo/train/log_1/events.out.tfevents.1532007504.ywz-PC -------------------------------------------------------------------------------- /Chapter14/save/minecraftbasic-v0/train/log_0/events.out.tfevents.1532007895.ywz-PC: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter14/save/minecraftbasic-v0/train/log_0/events.out.tfevents.1532007895.ywz-PC -------------------------------------------------------------------------------- /Chapter14/test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter14/test.py -------------------------------------------------------------------------------- /Chapter14/timer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter14/timer.py -------------------------------------------------------------------------------- /Chapter14/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter14/train.py -------------------------------------------------------------------------------- /Chapter14/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter14/utils.py -------------------------------------------------------------------------------- /Chapter14/worker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter14/worker.py -------------------------------------------------------------------------------- /Chapter15/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /Chapter15/commands.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter15/commands.txt -------------------------------------------------------------------------------- /Chapter15/src/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /Chapter15/src/alphagozero_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter15/src/alphagozero_agent.py -------------------------------------------------------------------------------- /Chapter15/src/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter15/src/config.py -------------------------------------------------------------------------------- /Chapter15/src/constants.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter15/src/constants.py -------------------------------------------------------------------------------- /Chapter15/src/controller.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter15/src/controller.py -------------------------------------------------------------------------------- /Chapter15/src/features.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter15/src/features.py -------------------------------------------------------------------------------- /Chapter15/src/go.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter15/src/go.py -------------------------------------------------------------------------------- /Chapter15/src/mcts.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter15/src/mcts.py -------------------------------------------------------------------------------- /Chapter15/src/network.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter15/src/network.py -------------------------------------------------------------------------------- /Chapter15/src/preprocessing.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter15/src/preprocessing.py -------------------------------------------------------------------------------- /Chapter15/src/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter15/src/train.py -------------------------------------------------------------------------------- /Chapter15/src/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter15/src/utils.py -------------------------------------------------------------------------------- /Chapter16/RL chatbot.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter16/RL chatbot.ipynb -------------------------------------------------------------------------------- /Chapter16/convert_checkpoint.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /Chapter16/data_parser.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter16/data_parser.py -------------------------------------------------------------------------------- /Chapter16/data_reader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter16/data_reader.py -------------------------------------------------------------------------------- /Chapter16/feature_extracter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter16/feature_extracter.py -------------------------------------------------------------------------------- /Chapter16/model/Reversed/checkpoint: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter16/model/Reversed/checkpoint -------------------------------------------------------------------------------- /Chapter16/model/model-56-3000/checkpoint: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter16/model/model-56-3000/checkpoint -------------------------------------------------------------------------------- /Chapter16/pg_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter16/pg_model.py -------------------------------------------------------------------------------- /Chapter16/results/sample_input.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter16/results/sample_input.txt -------------------------------------------------------------------------------- /Chapter16/results/sample_output_RL.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter16/results/sample_output_RL.txt -------------------------------------------------------------------------------- /Chapter16/seq_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter16/seq_model.py -------------------------------------------------------------------------------- /Chapter16/test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter16/test.py -------------------------------------------------------------------------------- /Chapter16/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter16/train.py -------------------------------------------------------------------------------- /Chapter17/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter17/README.md -------------------------------------------------------------------------------- /Chapter17/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /Chapter17/src/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /Chapter17/src/child_network.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter17/src/child_network.py -------------------------------------------------------------------------------- /Chapter17/src/cifar10_processor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter17/src/cifar10_processor.py -------------------------------------------------------------------------------- /Chapter17/src/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter17/src/config.py -------------------------------------------------------------------------------- /Chapter17/src/constants.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter17/src/constants.py -------------------------------------------------------------------------------- /Chapter17/src/controller.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter17/src/controller.py -------------------------------------------------------------------------------- /Chapter17/src/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter17/src/train.py -------------------------------------------------------------------------------- /Chapter18/actor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter18/actor.py -------------------------------------------------------------------------------- /Chapter18/agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter18/agent.py -------------------------------------------------------------------------------- /Chapter18/critic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter18/critic.py -------------------------------------------------------------------------------- /Chapter18/helper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter18/helper.py -------------------------------------------------------------------------------- /Chapter18/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter18/train.py -------------------------------------------------------------------------------- /Chapter19/.ipynb_checkpoints/13.3 Deep Q Learning From Demonstrations-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter19/.ipynb_checkpoints/13.3 Deep Q Learning From Demonstrations-checkpoint.ipynb -------------------------------------------------------------------------------- /Chapter19/.ipynb_checkpoints/13.4 Hindsight Experience Replay-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter19/.ipynb_checkpoints/13.4 Hindsight Experience Replay-checkpoint.ipynb -------------------------------------------------------------------------------- /Chapter19/13.3 Deep Q Learning From Demonstrations.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter19/13.3 Deep Q Learning From Demonstrations.ipynb -------------------------------------------------------------------------------- /Chapter19/13.4 Hindsight Experience Replay.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter19/13.4 Hindsight Experience Replay.ipynb -------------------------------------------------------------------------------- /Chapter19/images/B09792_13_01.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter19/images/B09792_13_01.png -------------------------------------------------------------------------------- /Chapter19/images/B09792_13_02.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/Chapter19/images/B09792_13_02.png -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Python-Reinforcement-Learning/HEAD/README.md --------------------------------------------------------------------------------