├── Contributing.md ├── Installation_steps.pdf ├── LICENSE.txt ├── README.md ├── chapter10 ├── 10.a-dynaQ.ipynb ├── 10.b-explore-vs-exploit.ipynb └── images │ └── cliffworld.png ├── chapter11 ├── 11.a-kl_inspiration.ipynb └── 11.b-gpt2_sentiment.ipynb ├── chapter12 └── 12.a-ppo_pettingzoo_kaz.ipynb ├── chapter2 ├── 2.a-RL-environment.ipynb ├── 2.b-RL-components.ipynb ├── 2.c-First-Agent.ipynb ├── 2.d-Second_Agent.ipynb ├── 2.e-RL-Zoo.ipynb └── images │ ├── mc_episodic.png │ ├── mcchain_continuing.png │ └── mrp_continuing.png ├── chapter3 ├── 3.a-policy-evaluation.ipynb ├── 3.b-policy-iteration.ipynb ├── 3.c-value-iteration.ipynb ├── gridworld.py └── images │ ├── gridworld.png │ └── policy_iteration_backup.png ├── chapter4 ├── 4.a-mc_estimation.ipynb ├── 4.b-mc_control.ipynb ├── 4.c-sarsa-on-policy.ipynb ├── 4.d-qlearning.ipynb ├── 4.e-expected_sarsa.ipynb ├── 4.f-qlearning-exp-replay.ipynb ├── 4.g-qlearning_continuous_env.ipynb ├── gridworld.py └── images │ ├── cliffworld.png │ ├── gridworld.png │ └── mc_backup.png ├── chapter5 ├── 5.a-n-step-SARSA.ipynb ├── 5.b-lambda-sarsa.ipynb ├── 5.c-Intro-to-pytorch.ipynb ├── 5.d-Intro-to-pytorch-lightning.ipynb ├── 5.e-Intro-to-tensorflow.ipynb ├── images │ ├── neuron.png │ ├── nn.svg │ └── nstepSarsa.png └── tiles3.py ├── chapter6 ├── 6.a-dqn-pytorch.ipynb ├── 6.b-dqn-tensorflow.ipynb ├── 6.c-dqn_atari_pytorch.ipynb ├── 6.d-robotic-envs.ipynb ├── 6.e-dqn_flappy_pytorch.ipynb ├── images │ ├── dueling_network.png │ └── pyramids.png └── ppo_config_6e.py ├── chapter7 ├── 7.a-dqn_prioritized_replay.ipynb ├── 7.b-ddqn.ipynb ├── 7.c-dueling_dqn.ipynb ├── 7.d-noisynet_dqn.ipynb ├── 7.e-c51_dqn.ipynb ├── 7.f-qr_dqn.ipynb ├── 7.g-her_dqn.ipynb └── images │ └── dueling_network.png ├── chapter8 ├── 8.a-reinforce.ipynb ├── 8.b-actor_critic.ipynb ├── 8.c-ppo_sb3.ipynb └── images │ └── actor_critic.png ├── chapter9 ├── 9.a-ddpg.ipynb ├── 9.b-td3.ipynb ├── 9.c-reparam.ipynb ├── 9.d-entropy_bernoulli.ipynb └── 9.e-sac.ipynb ├── requirements.txt └── requirements_old.txt /Contributing.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Apress/Deep-Reinforcement-Learning-with-Python/HEAD/Contributing.md -------------------------------------------------------------------------------- /Installation_steps.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Apress/Deep-Reinforcement-Learning-with-Python/HEAD/Installation_steps.pdf -------------------------------------------------------------------------------- /LICENSE.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Apress/Deep-Reinforcement-Learning-with-Python/HEAD/LICENSE.txt -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Apress/Deep-Reinforcement-Learning-with-Python/HEAD/README.md -------------------------------------------------------------------------------- /chapter10/10.a-dynaQ.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Apress/Deep-Reinforcement-Learning-with-Python/HEAD/chapter10/10.a-dynaQ.ipynb -------------------------------------------------------------------------------- /chapter10/10.b-explore-vs-exploit.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Apress/Deep-Reinforcement-Learning-with-Python/HEAD/chapter10/10.b-explore-vs-exploit.ipynb -------------------------------------------------------------------------------- /chapter10/images/cliffworld.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Apress/Deep-Reinforcement-Learning-with-Python/HEAD/chapter10/images/cliffworld.png -------------------------------------------------------------------------------- /chapter11/11.a-kl_inspiration.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Apress/Deep-Reinforcement-Learning-with-Python/HEAD/chapter11/11.a-kl_inspiration.ipynb -------------------------------------------------------------------------------- /chapter11/11.b-gpt2_sentiment.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Apress/Deep-Reinforcement-Learning-with-Python/HEAD/chapter11/11.b-gpt2_sentiment.ipynb -------------------------------------------------------------------------------- /chapter12/12.a-ppo_pettingzoo_kaz.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Apress/Deep-Reinforcement-Learning-with-Python/HEAD/chapter12/12.a-ppo_pettingzoo_kaz.ipynb -------------------------------------------------------------------------------- /chapter2/2.a-RL-environment.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Apress/Deep-Reinforcement-Learning-with-Python/HEAD/chapter2/2.a-RL-environment.ipynb -------------------------------------------------------------------------------- /chapter2/2.b-RL-components.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Apress/Deep-Reinforcement-Learning-with-Python/HEAD/chapter2/2.b-RL-components.ipynb -------------------------------------------------------------------------------- /chapter2/2.c-First-Agent.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Apress/Deep-Reinforcement-Learning-with-Python/HEAD/chapter2/2.c-First-Agent.ipynb -------------------------------------------------------------------------------- /chapter2/2.d-Second_Agent.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Apress/Deep-Reinforcement-Learning-with-Python/HEAD/chapter2/2.d-Second_Agent.ipynb -------------------------------------------------------------------------------- /chapter2/2.e-RL-Zoo.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Apress/Deep-Reinforcement-Learning-with-Python/HEAD/chapter2/2.e-RL-Zoo.ipynb -------------------------------------------------------------------------------- /chapter2/images/mc_episodic.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Apress/Deep-Reinforcement-Learning-with-Python/HEAD/chapter2/images/mc_episodic.png -------------------------------------------------------------------------------- /chapter2/images/mcchain_continuing.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Apress/Deep-Reinforcement-Learning-with-Python/HEAD/chapter2/images/mcchain_continuing.png -------------------------------------------------------------------------------- /chapter2/images/mrp_continuing.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Apress/Deep-Reinforcement-Learning-with-Python/HEAD/chapter2/images/mrp_continuing.png -------------------------------------------------------------------------------- /chapter3/3.a-policy-evaluation.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Apress/Deep-Reinforcement-Learning-with-Python/HEAD/chapter3/3.a-policy-evaluation.ipynb -------------------------------------------------------------------------------- /chapter3/3.b-policy-iteration.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Apress/Deep-Reinforcement-Learning-with-Python/HEAD/chapter3/3.b-policy-iteration.ipynb -------------------------------------------------------------------------------- /chapter3/3.c-value-iteration.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Apress/Deep-Reinforcement-Learning-with-Python/HEAD/chapter3/3.c-value-iteration.ipynb -------------------------------------------------------------------------------- /chapter3/gridworld.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Apress/Deep-Reinforcement-Learning-with-Python/HEAD/chapter3/gridworld.py -------------------------------------------------------------------------------- /chapter3/images/gridworld.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Apress/Deep-Reinforcement-Learning-with-Python/HEAD/chapter3/images/gridworld.png -------------------------------------------------------------------------------- /chapter3/images/policy_iteration_backup.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Apress/Deep-Reinforcement-Learning-with-Python/HEAD/chapter3/images/policy_iteration_backup.png -------------------------------------------------------------------------------- /chapter4/4.a-mc_estimation.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Apress/Deep-Reinforcement-Learning-with-Python/HEAD/chapter4/4.a-mc_estimation.ipynb -------------------------------------------------------------------------------- /chapter4/4.b-mc_control.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Apress/Deep-Reinforcement-Learning-with-Python/HEAD/chapter4/4.b-mc_control.ipynb -------------------------------------------------------------------------------- /chapter4/4.c-sarsa-on-policy.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Apress/Deep-Reinforcement-Learning-with-Python/HEAD/chapter4/4.c-sarsa-on-policy.ipynb -------------------------------------------------------------------------------- /chapter4/4.d-qlearning.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Apress/Deep-Reinforcement-Learning-with-Python/HEAD/chapter4/4.d-qlearning.ipynb -------------------------------------------------------------------------------- /chapter4/4.e-expected_sarsa.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Apress/Deep-Reinforcement-Learning-with-Python/HEAD/chapter4/4.e-expected_sarsa.ipynb -------------------------------------------------------------------------------- /chapter4/4.f-qlearning-exp-replay.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Apress/Deep-Reinforcement-Learning-with-Python/HEAD/chapter4/4.f-qlearning-exp-replay.ipynb -------------------------------------------------------------------------------- /chapter4/4.g-qlearning_continuous_env.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Apress/Deep-Reinforcement-Learning-with-Python/HEAD/chapter4/4.g-qlearning_continuous_env.ipynb -------------------------------------------------------------------------------- /chapter4/gridworld.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Apress/Deep-Reinforcement-Learning-with-Python/HEAD/chapter4/gridworld.py -------------------------------------------------------------------------------- /chapter4/images/cliffworld.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Apress/Deep-Reinforcement-Learning-with-Python/HEAD/chapter4/images/cliffworld.png -------------------------------------------------------------------------------- /chapter4/images/gridworld.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Apress/Deep-Reinforcement-Learning-with-Python/HEAD/chapter4/images/gridworld.png -------------------------------------------------------------------------------- /chapter4/images/mc_backup.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Apress/Deep-Reinforcement-Learning-with-Python/HEAD/chapter4/images/mc_backup.png -------------------------------------------------------------------------------- /chapter5/5.a-n-step-SARSA.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Apress/Deep-Reinforcement-Learning-with-Python/HEAD/chapter5/5.a-n-step-SARSA.ipynb -------------------------------------------------------------------------------- /chapter5/5.b-lambda-sarsa.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Apress/Deep-Reinforcement-Learning-with-Python/HEAD/chapter5/5.b-lambda-sarsa.ipynb -------------------------------------------------------------------------------- /chapter5/5.c-Intro-to-pytorch.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Apress/Deep-Reinforcement-Learning-with-Python/HEAD/chapter5/5.c-Intro-to-pytorch.ipynb -------------------------------------------------------------------------------- /chapter5/5.d-Intro-to-pytorch-lightning.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Apress/Deep-Reinforcement-Learning-with-Python/HEAD/chapter5/5.d-Intro-to-pytorch-lightning.ipynb -------------------------------------------------------------------------------- /chapter5/5.e-Intro-to-tensorflow.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Apress/Deep-Reinforcement-Learning-with-Python/HEAD/chapter5/5.e-Intro-to-tensorflow.ipynb -------------------------------------------------------------------------------- /chapter5/images/neuron.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Apress/Deep-Reinforcement-Learning-with-Python/HEAD/chapter5/images/neuron.png -------------------------------------------------------------------------------- /chapter5/images/nn.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Apress/Deep-Reinforcement-Learning-with-Python/HEAD/chapter5/images/nn.svg -------------------------------------------------------------------------------- /chapter5/images/nstepSarsa.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Apress/Deep-Reinforcement-Learning-with-Python/HEAD/chapter5/images/nstepSarsa.png -------------------------------------------------------------------------------- /chapter5/tiles3.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Apress/Deep-Reinforcement-Learning-with-Python/HEAD/chapter5/tiles3.py -------------------------------------------------------------------------------- /chapter6/6.a-dqn-pytorch.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Apress/Deep-Reinforcement-Learning-with-Python/HEAD/chapter6/6.a-dqn-pytorch.ipynb -------------------------------------------------------------------------------- /chapter6/6.b-dqn-tensorflow.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Apress/Deep-Reinforcement-Learning-with-Python/HEAD/chapter6/6.b-dqn-tensorflow.ipynb -------------------------------------------------------------------------------- /chapter6/6.c-dqn_atari_pytorch.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Apress/Deep-Reinforcement-Learning-with-Python/HEAD/chapter6/6.c-dqn_atari_pytorch.ipynb -------------------------------------------------------------------------------- /chapter6/6.d-robotic-envs.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Apress/Deep-Reinforcement-Learning-with-Python/HEAD/chapter6/6.d-robotic-envs.ipynb -------------------------------------------------------------------------------- /chapter6/6.e-dqn_flappy_pytorch.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Apress/Deep-Reinforcement-Learning-with-Python/HEAD/chapter6/6.e-dqn_flappy_pytorch.ipynb -------------------------------------------------------------------------------- /chapter6/images/dueling_network.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Apress/Deep-Reinforcement-Learning-with-Python/HEAD/chapter6/images/dueling_network.png -------------------------------------------------------------------------------- /chapter6/images/pyramids.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Apress/Deep-Reinforcement-Learning-with-Python/HEAD/chapter6/images/pyramids.png -------------------------------------------------------------------------------- /chapter6/ppo_config_6e.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Apress/Deep-Reinforcement-Learning-with-Python/HEAD/chapter6/ppo_config_6e.py -------------------------------------------------------------------------------- /chapter7/7.a-dqn_prioritized_replay.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Apress/Deep-Reinforcement-Learning-with-Python/HEAD/chapter7/7.a-dqn_prioritized_replay.ipynb -------------------------------------------------------------------------------- /chapter7/7.b-ddqn.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Apress/Deep-Reinforcement-Learning-with-Python/HEAD/chapter7/7.b-ddqn.ipynb -------------------------------------------------------------------------------- /chapter7/7.c-dueling_dqn.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Apress/Deep-Reinforcement-Learning-with-Python/HEAD/chapter7/7.c-dueling_dqn.ipynb -------------------------------------------------------------------------------- /chapter7/7.d-noisynet_dqn.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Apress/Deep-Reinforcement-Learning-with-Python/HEAD/chapter7/7.d-noisynet_dqn.ipynb -------------------------------------------------------------------------------- /chapter7/7.e-c51_dqn.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Apress/Deep-Reinforcement-Learning-with-Python/HEAD/chapter7/7.e-c51_dqn.ipynb -------------------------------------------------------------------------------- /chapter7/7.f-qr_dqn.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Apress/Deep-Reinforcement-Learning-with-Python/HEAD/chapter7/7.f-qr_dqn.ipynb -------------------------------------------------------------------------------- /chapter7/7.g-her_dqn.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Apress/Deep-Reinforcement-Learning-with-Python/HEAD/chapter7/7.g-her_dqn.ipynb -------------------------------------------------------------------------------- /chapter7/images/dueling_network.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Apress/Deep-Reinforcement-Learning-with-Python/HEAD/chapter7/images/dueling_network.png -------------------------------------------------------------------------------- /chapter8/8.a-reinforce.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Apress/Deep-Reinforcement-Learning-with-Python/HEAD/chapter8/8.a-reinforce.ipynb -------------------------------------------------------------------------------- /chapter8/8.b-actor_critic.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Apress/Deep-Reinforcement-Learning-with-Python/HEAD/chapter8/8.b-actor_critic.ipynb -------------------------------------------------------------------------------- /chapter8/8.c-ppo_sb3.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Apress/Deep-Reinforcement-Learning-with-Python/HEAD/chapter8/8.c-ppo_sb3.ipynb -------------------------------------------------------------------------------- /chapter8/images/actor_critic.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Apress/Deep-Reinforcement-Learning-with-Python/HEAD/chapter8/images/actor_critic.png -------------------------------------------------------------------------------- /chapter9/9.a-ddpg.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Apress/Deep-Reinforcement-Learning-with-Python/HEAD/chapter9/9.a-ddpg.ipynb -------------------------------------------------------------------------------- /chapter9/9.b-td3.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Apress/Deep-Reinforcement-Learning-with-Python/HEAD/chapter9/9.b-td3.ipynb -------------------------------------------------------------------------------- /chapter9/9.c-reparam.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Apress/Deep-Reinforcement-Learning-with-Python/HEAD/chapter9/9.c-reparam.ipynb -------------------------------------------------------------------------------- /chapter9/9.d-entropy_bernoulli.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Apress/Deep-Reinforcement-Learning-with-Python/HEAD/chapter9/9.d-entropy_bernoulli.ipynb -------------------------------------------------------------------------------- /chapter9/9.e-sac.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Apress/Deep-Reinforcement-Learning-with-Python/HEAD/chapter9/9.e-sac.ipynb -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Apress/Deep-Reinforcement-Learning-with-Python/HEAD/requirements.txt -------------------------------------------------------------------------------- /requirements_old.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Apress/Deep-Reinforcement-Learning-with-Python/HEAD/requirements_old.txt --------------------------------------------------------------------------------