├── 01. Introduction to Reinforcement Learning ├── .ipynb_checkpoints │ └── 1.1 What is Reinforcement Learning-checkpoint.ipynb ├── 1.1 What is Reinforcement Learning.ipynb └── images │ ├── B09792_01_01.png │ ├── B09792_01_02.png │ └── B09792_01_03.png ├── 02. Getting Started with OpenAI and Tensorflow ├── .ipynb_checkpoints │ ├── Video Game Bot using OpenAI Universe-checkpoint.ipynb │ ├── 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 ├── 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 ├── 03. Markov Decision Process and Dynamic Programming ├── .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 ├── 04. Gaming with Monte Carlo Methods ├── .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 ├── 05. Temporal Difference Learning ├── .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 ├── 06. Multi-Armed Bandit Problem ├── .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 ├── 07. Deep Learning Fundamentals ├── .ipynb_checkpoints │ ├── 7.10 Generating Song Lyrics Using LSTM RNN-checkpoint.ipynb │ ├── 7.13 Classifying Fashion Products Using CNN-checkpoint.ipynb │ └── 7.6 Neural Network Using Tensorflow-checkpoint.ipynb ├── 7.10 Generating Song Lyrics Using LSTM RNN.ipynb ├── 7.13 Classifying Fashion Products Using CNN.ipynb ├── 7.6 Neural Network Using Tensorflow.ipynb └── data │ ├── ZaynLyrics.txt │ ├── fashion │ ├── t10k-images-idx3-ubyte.gz │ ├── t10k-labels-idx1-ubyte.gz │ ├── train-images-idx3-ubyte.gz │ └── train-labels-idx1-ubyte.gz │ └── mnist │ ├── t10k-images-idx3-ubyte.gz │ ├── t10k-labels-idx1-ubyte.gz │ ├── train-images-idx3-ubyte.gz │ └── train-labels-idx1-ubyte.gz ├── 08. Atari Games with DQN ├── .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 ├── 09. Playing Doom Game using DRQN ├── .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 ├── 10. Aysnchronous Advantage Actor Critic Network ├── .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 ├── 11. Policy Gradients and Optimization ├── .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 ├── 12. Capstone Project: Car Racing using DQN ├── .ipynb_checkpoints │ ├── 12.1 Environment Wrapper Functions-checkpoint.ipynb │ ├── 12.2 Dueling network-checkpoint.ipynb │ ├── 12.3 Replay Memory-checkpoint.ipynb │ ├── 12.4 Training the network-checkpoint.ipynb │ └── 12.5 Car Racing-checkpoint.ipynb ├── 12.1 Environment Wrapper Functions.ipynb ├── 12.2 Dueling network.ipynb ├── 12.3 Replay Memory.ipynb ├── 12.4 Training the network.ipynb └── 12.5 Car Racing.ipynb ├── 13. Recent Advancements and Next Steps ├── .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 ├── README.md └── images ├── Oreilly_safari_logo.png ├── amazon_logo.jpg ├── book_cover.jpg ├── googlebooks_logo.png ├── googleplay_logo.png ├── packt_logo.jpeg └── packt_logo.jpg /01. Introduction to Reinforcement Learning/.ipynb_checkpoints/1.1 What is Reinforcement Learning-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/01. Introduction to Reinforcement Learning/.ipynb_checkpoints/1.1 What is Reinforcement Learning-checkpoint.ipynb -------------------------------------------------------------------------------- /01. Introduction to Reinforcement Learning/1.1 What is Reinforcement Learning.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/01. Introduction to Reinforcement Learning/1.1 What is Reinforcement Learning.ipynb -------------------------------------------------------------------------------- /01. Introduction to Reinforcement Learning/images/B09792_01_01.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/01. Introduction to Reinforcement Learning/images/B09792_01_01.png -------------------------------------------------------------------------------- /01. Introduction to Reinforcement Learning/images/B09792_01_02.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/01. Introduction to Reinforcement Learning/images/B09792_01_02.png -------------------------------------------------------------------------------- /01. Introduction to Reinforcement Learning/images/B09792_01_03.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/01. Introduction to Reinforcement Learning/images/B09792_01_03.png -------------------------------------------------------------------------------- /02. Getting Started with OpenAI and Tensorflow/.ipynb_checkpoints/ Video Game Bot using OpenAI Universe-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/02. Getting Started with OpenAI and Tensorflow/.ipynb_checkpoints/ Video Game Bot using OpenAI Universe-checkpoint.ipynb -------------------------------------------------------------------------------- /02. Getting Started with OpenAI and Tensorflow/.ipynb_checkpoints/2.09 Building a Video Game Bot -checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/02. Getting Started with OpenAI and Tensorflow/.ipynb_checkpoints/2.09 Building a Video Game Bot -checkpoint.ipynb -------------------------------------------------------------------------------- /02. Getting Started with OpenAI and Tensorflow/.ipynb_checkpoints/2.1 Basic Simulations-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/02. Getting Started with OpenAI and Tensorflow/.ipynb_checkpoints/2.1 Basic Simulations-checkpoint.ipynb -------------------------------------------------------------------------------- /02. Getting Started with OpenAI and Tensorflow/.ipynb_checkpoints/2.10 TensorFlow Fundamentals-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/02. Getting Started with OpenAI and Tensorflow/.ipynb_checkpoints/2.10 TensorFlow Fundamentals-checkpoint.ipynb -------------------------------------------------------------------------------- /02. Getting Started with OpenAI and Tensorflow/.ipynb_checkpoints/2.11 TensorBoard-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/02. Getting Started with OpenAI and Tensorflow/.ipynb_checkpoints/2.11 TensorBoard-checkpoint.ipynb -------------------------------------------------------------------------------- /02. Getting Started with OpenAI and Tensorflow/.ipynb_checkpoints/2.2 Training an agent to Walk-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/02. Getting Started with OpenAI and Tensorflow/.ipynb_checkpoints/2.2 Training an agent to Walk-checkpoint.ipynb -------------------------------------------------------------------------------- /02. Getting Started with OpenAI and Tensorflow/.ipynb_checkpoints/2.7 Basic Simulations-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/02. Getting Started with OpenAI and Tensorflow/.ipynb_checkpoints/2.7 Basic Simulations-checkpoint.ipynb -------------------------------------------------------------------------------- /02. Getting Started with OpenAI and Tensorflow/.ipynb_checkpoints/2.8 Training an Robot to Walk-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/02. Getting Started with OpenAI and Tensorflow/.ipynb_checkpoints/2.8 Training an Robot to Walk-checkpoint.ipynb -------------------------------------------------------------------------------- /02. Getting Started with OpenAI and Tensorflow/.ipynb_checkpoints/2.9 Building a Video Game Bot -checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/02. Getting Started with OpenAI and Tensorflow/.ipynb_checkpoints/2.9 Building a Video Game Bot -checkpoint.ipynb -------------------------------------------------------------------------------- /02. Getting Started with OpenAI and Tensorflow/.ipynb_checkpoints/TensorBoard-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/02. Getting Started with OpenAI and Tensorflow/.ipynb_checkpoints/TensorBoard-checkpoint.ipynb -------------------------------------------------------------------------------- /02. Getting Started with OpenAI and Tensorflow/.ipynb_checkpoints/TensorFlow Basics-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/02. Getting Started with OpenAI and Tensorflow/.ipynb_checkpoints/TensorFlow Basics-checkpoint.ipynb -------------------------------------------------------------------------------- /02. Getting Started with OpenAI and Tensorflow/2.07 Basic Simulations.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/02. Getting Started with OpenAI and Tensorflow/2.07 Basic Simulations.ipynb -------------------------------------------------------------------------------- /02. Getting Started with OpenAI and Tensorflow/2.08 Training an Robot to Walk.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/02. Getting Started with OpenAI and Tensorflow/2.08 Training an Robot to Walk.ipynb -------------------------------------------------------------------------------- /02. Getting Started with OpenAI and Tensorflow/2.09 Building a Video Game Bot .ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/02. Getting Started with OpenAI and Tensorflow/2.09 Building a Video Game Bot .ipynb -------------------------------------------------------------------------------- /02. Getting Started with OpenAI and Tensorflow/2.10 TensorFlow Fundamentals.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/02. Getting Started with OpenAI and Tensorflow/2.10 TensorFlow Fundamentals.ipynb -------------------------------------------------------------------------------- /02. Getting Started with OpenAI and Tensorflow/2.11 TensorBoard.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/02. Getting Started with OpenAI and Tensorflow/2.11 TensorBoard.ipynb -------------------------------------------------------------------------------- /02. Getting Started with OpenAI and Tensorflow/logs/events.out.tfevents.1527762800.sudharsan: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/02. Getting Started with OpenAI and Tensorflow/logs/events.out.tfevents.1527762800.sudharsan -------------------------------------------------------------------------------- /03. Markov Decision Process and Dynamic Programming/.ipynb_checkpoints/3.1 Value Iteration - Frozen Lake Problem-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/03. Markov Decision Process and Dynamic Programming/.ipynb_checkpoints/3.1 Value Iteration - Frozen Lake Problem-checkpoint.ipynb -------------------------------------------------------------------------------- /03. Markov Decision Process and Dynamic Programming/.ipynb_checkpoints/3.12 Value Iteration - Frozen Lake Problem-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/03. Markov Decision Process and Dynamic Programming/.ipynb_checkpoints/3.12 Value Iteration - Frozen Lake Problem-checkpoint.ipynb -------------------------------------------------------------------------------- /03. Markov Decision Process and Dynamic Programming/.ipynb_checkpoints/3.13 Policy Iteration - Frozen Lake Problem-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/03. Markov Decision Process and Dynamic Programming/.ipynb_checkpoints/3.13 Policy Iteration - Frozen Lake Problem-checkpoint.ipynb -------------------------------------------------------------------------------- /03. Markov Decision Process and Dynamic Programming/.ipynb_checkpoints/3.2 Policy Iteration - Frozen Lake Problem-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/03. Markov Decision Process and Dynamic Programming/.ipynb_checkpoints/3.2 Policy Iteration - Frozen Lake Problem-checkpoint.ipynb -------------------------------------------------------------------------------- /03. Markov Decision Process and Dynamic Programming/3.12 Value Iteration - Frozen Lake Problem.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/03. Markov Decision Process and Dynamic Programming/3.12 Value Iteration - Frozen Lake Problem.ipynb -------------------------------------------------------------------------------- /03. Markov Decision Process and Dynamic Programming/3.13 Policy Iteration - Frozen Lake Problem.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/03. Markov Decision Process and Dynamic Programming/3.13 Policy Iteration - Frozen Lake Problem.ipynb -------------------------------------------------------------------------------- /03. Markov Decision Process and Dynamic Programming/images/B09792_03_50.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/03. Markov Decision Process and Dynamic Programming/images/B09792_03_50.png -------------------------------------------------------------------------------- /04. Gaming with Monte Carlo Methods/.ipynb_checkpoints/4.1 Estimating Value of Pi using Monte Carlo-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/04. Gaming with Monte Carlo Methods/.ipynb_checkpoints/4.1 Estimating Value of Pi using Monte Carlo-checkpoint.ipynb -------------------------------------------------------------------------------- /04. Gaming with Monte Carlo Methods/.ipynb_checkpoints/4.2 BlackJack with First visit MC-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/04. Gaming with Monte Carlo Methods/.ipynb_checkpoints/4.2 BlackJack with First visit MC-checkpoint.ipynb -------------------------------------------------------------------------------- /04. Gaming with Monte Carlo Methods/.ipynb_checkpoints/4.2 Estimating Value of Pi using Monte Carlo-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/04. Gaming with Monte Carlo Methods/.ipynb_checkpoints/4.2 Estimating Value of Pi using Monte Carlo-checkpoint.ipynb -------------------------------------------------------------------------------- /04. Gaming with Monte Carlo Methods/.ipynb_checkpoints/4.6 BlackJack with First visit MC-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/04. Gaming with Monte Carlo Methods/.ipynb_checkpoints/4.6 BlackJack with First visit MC-checkpoint.ipynb -------------------------------------------------------------------------------- /04. Gaming with Monte Carlo Methods/4.2 Estimating Value of Pi using Monte Carlo.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/04. Gaming with Monte Carlo Methods/4.2 Estimating Value of Pi using Monte Carlo.ipynb -------------------------------------------------------------------------------- /04. Gaming with Monte Carlo Methods/4.6 BlackJack with First visit MC.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/04. Gaming with Monte Carlo Methods/4.6 BlackJack with First visit MC.ipynb -------------------------------------------------------------------------------- /05. Temporal Difference Learning/.ipynb_checkpoints/5.5 Taxi Problem - Q Learning-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/05. Temporal Difference Learning/.ipynb_checkpoints/5.5 Taxi Problem - Q Learning-checkpoint.ipynb -------------------------------------------------------------------------------- /05. Temporal Difference Learning/.ipynb_checkpoints/5.7 Taxi Problem - SARSA-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/05. Temporal Difference Learning/.ipynb_checkpoints/5.7 Taxi Problem - SARSA-checkpoint.ipynb -------------------------------------------------------------------------------- /05. Temporal Difference Learning/5.5 Taxi Problem - Q Learning.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/05. Temporal Difference Learning/5.5 Taxi Problem - Q Learning.ipynb -------------------------------------------------------------------------------- /05. Temporal Difference Learning/5.7 Taxi Problem - SARSA.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/05. Temporal Difference Learning/5.7 Taxi Problem - SARSA.ipynb -------------------------------------------------------------------------------- /06. Multi-Armed Bandit Problem/.ipynb_checkpoints/6.1 MAB - Various Exploration Strategies-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/06. Multi-Armed Bandit Problem/.ipynb_checkpoints/6.1 MAB - Various Exploration Strategies-checkpoint.ipynb -------------------------------------------------------------------------------- /06. Multi-Armed Bandit Problem/.ipynb_checkpoints/6.7 Identifying Right AD Banner Using MAB-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/06. Multi-Armed Bandit Problem/.ipynb_checkpoints/6.7 Identifying Right AD Banner Using MAB-checkpoint.ipynb -------------------------------------------------------------------------------- /06. Multi-Armed Bandit Problem/6.1 MAB - Various Exploration Strategies.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/06. Multi-Armed Bandit Problem/6.1 MAB - Various Exploration Strategies.ipynb -------------------------------------------------------------------------------- /06. Multi-Armed Bandit Problem/6.7 Identifying Right AD Banner Using MAB.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/06. Multi-Armed Bandit Problem/6.7 Identifying Right AD Banner Using MAB.ipynb -------------------------------------------------------------------------------- /06. Multi-Armed Bandit Problem/images/B09792_06_01.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/06. Multi-Armed Bandit Problem/images/B09792_06_01.png -------------------------------------------------------------------------------- /07. Deep Learning Fundamentals/.ipynb_checkpoints/7.10 Generating Song Lyrics Using LSTM RNN-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/07. Deep Learning Fundamentals/.ipynb_checkpoints/7.10 Generating Song Lyrics Using LSTM RNN-checkpoint.ipynb -------------------------------------------------------------------------------- /07. Deep Learning Fundamentals/.ipynb_checkpoints/7.13 Classifying Fashion Products Using CNN-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/07. Deep Learning Fundamentals/.ipynb_checkpoints/7.13 Classifying Fashion Products Using CNN-checkpoint.ipynb -------------------------------------------------------------------------------- /07. Deep Learning Fundamentals/.ipynb_checkpoints/7.6 Neural Network Using Tensorflow-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/07. Deep Learning Fundamentals/.ipynb_checkpoints/7.6 Neural Network Using Tensorflow-checkpoint.ipynb -------------------------------------------------------------------------------- /07. Deep Learning Fundamentals/7.10 Generating Song Lyrics Using LSTM RNN.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/07. Deep Learning Fundamentals/7.10 Generating Song Lyrics Using LSTM RNN.ipynb -------------------------------------------------------------------------------- /07. Deep Learning Fundamentals/7.13 Classifying Fashion Products Using CNN.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/07. Deep Learning Fundamentals/7.13 Classifying Fashion Products Using CNN.ipynb -------------------------------------------------------------------------------- /07. Deep Learning Fundamentals/7.6 Neural Network Using Tensorflow.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/07. Deep Learning Fundamentals/7.6 Neural Network Using Tensorflow.ipynb -------------------------------------------------------------------------------- /07. Deep Learning Fundamentals/data/ZaynLyrics.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/07. Deep Learning Fundamentals/data/ZaynLyrics.txt -------------------------------------------------------------------------------- /07. Deep Learning Fundamentals/data/fashion/t10k-images-idx3-ubyte.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/07. Deep Learning Fundamentals/data/fashion/t10k-images-idx3-ubyte.gz -------------------------------------------------------------------------------- /07. Deep Learning Fundamentals/data/fashion/t10k-labels-idx1-ubyte.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/07. Deep Learning Fundamentals/data/fashion/t10k-labels-idx1-ubyte.gz -------------------------------------------------------------------------------- /07. Deep Learning Fundamentals/data/fashion/train-images-idx3-ubyte.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/07. Deep Learning Fundamentals/data/fashion/train-images-idx3-ubyte.gz -------------------------------------------------------------------------------- /07. Deep Learning Fundamentals/data/fashion/train-labels-idx1-ubyte.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/07. Deep Learning Fundamentals/data/fashion/train-labels-idx1-ubyte.gz -------------------------------------------------------------------------------- /07. Deep Learning Fundamentals/data/mnist/t10k-images-idx3-ubyte.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/07. Deep Learning Fundamentals/data/mnist/t10k-images-idx3-ubyte.gz -------------------------------------------------------------------------------- /07. Deep Learning Fundamentals/data/mnist/t10k-labels-idx1-ubyte.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/07. Deep Learning Fundamentals/data/mnist/t10k-labels-idx1-ubyte.gz -------------------------------------------------------------------------------- /07. Deep Learning Fundamentals/data/mnist/train-images-idx3-ubyte.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/07. Deep Learning Fundamentals/data/mnist/train-images-idx3-ubyte.gz -------------------------------------------------------------------------------- /07. Deep Learning Fundamentals/data/mnist/train-labels-idx1-ubyte.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/07. Deep Learning Fundamentals/data/mnist/train-labels-idx1-ubyte.gz -------------------------------------------------------------------------------- /08. Atari Games with DQN/.ipynb_checkpoints/8.8 Building an Agent to Play Atari Games-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/08. Atari Games with DQN/.ipynb_checkpoints/8.8 Building an Agent to Play Atari Games-checkpoint.ipynb -------------------------------------------------------------------------------- /08. Atari Games with DQN/8.8 Building an Agent to Play Atari Games.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/08. Atari Games with DQN/8.8 Building an Agent to Play Atari Games.ipynb -------------------------------------------------------------------------------- /08. Atari Games with DQN/logs/events.out.tfevents.1526989751.sudharsan: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/08. Atari Games with DQN/logs/events.out.tfevents.1526989751.sudharsan -------------------------------------------------------------------------------- /08. Atari Games with DQN/logs/events.out.tfevents.1526990072.sudharsan: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/08. Atari Games with DQN/logs/events.out.tfevents.1526990072.sudharsan -------------------------------------------------------------------------------- /08. Atari Games with DQN/logs/events.out.tfevents.1528714237.sudharsan: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/08. Atari Games with DQN/logs/events.out.tfevents.1528714237.sudharsan -------------------------------------------------------------------------------- /09. Playing Doom Game using DRQN/.ipynb_checkpoints/9.4 Basic Doom Game-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/09. Playing Doom Game using DRQN/.ipynb_checkpoints/9.4 Basic Doom Game-checkpoint.ipynb -------------------------------------------------------------------------------- /09. Playing Doom Game using DRQN/.ipynb_checkpoints/9.5 Doom Game Using DRQN-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/09. Playing Doom Game using DRQN/.ipynb_checkpoints/9.5 Doom Game Using DRQN-checkpoint.ipynb -------------------------------------------------------------------------------- /09. Playing Doom Game using DRQN/9.4 Basic Doom Game.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/09. Playing Doom Game using DRQN/9.4 Basic Doom Game.ipynb -------------------------------------------------------------------------------- /09. Playing Doom Game using DRQN/9.5 Doom Game Using DRQN.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/09. Playing Doom Game using DRQN/9.5 Doom Game Using DRQN.ipynb -------------------------------------------------------------------------------- /09. Playing Doom Game using DRQN/basic.cfg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/09. Playing Doom Game using DRQN/basic.cfg -------------------------------------------------------------------------------- /09. Playing Doom Game using DRQN/basic.wad: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/09. Playing Doom Game using DRQN/basic.wad -------------------------------------------------------------------------------- /09. Playing Doom Game using DRQN/deathmatch.cfg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/09. Playing Doom Game using DRQN/deathmatch.cfg -------------------------------------------------------------------------------- /09. Playing Doom Game using DRQN/deathmatch.wad: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/09. Playing Doom Game using DRQN/deathmatch.wad -------------------------------------------------------------------------------- /10. Aysnchronous Advantage Actor Critic Network/.ipynb_checkpoints/10.5 Drive up the Mountain Using A3C-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/10. Aysnchronous Advantage Actor Critic Network/.ipynb_checkpoints/10.5 Drive up the Mountain Using A3C-checkpoint.ipynb -------------------------------------------------------------------------------- /10. Aysnchronous Advantage Actor Critic Network/10.5 Drive up the Mountain Using A3C.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/10. Aysnchronous Advantage Actor Critic Network/10.5 Drive up the Mountain Using A3C.ipynb -------------------------------------------------------------------------------- /10. Aysnchronous Advantage Actor Critic Network/logs/events.out.tfevents.1528713441.sudharsan: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/10. Aysnchronous Advantage Actor Critic Network/logs/events.out.tfevents.1528713441.sudharsan -------------------------------------------------------------------------------- /11. Policy Gradients and Optimization/.ipynb_checkpoints/11.2 Lunar Lander Using Policy Gradients-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/11. Policy Gradients and Optimization/.ipynb_checkpoints/11.2 Lunar Lander Using Policy Gradients-checkpoint.ipynb -------------------------------------------------------------------------------- /11. Policy Gradients and Optimization/.ipynb_checkpoints/11.3 Swinging Up the Pendulum Using DDPG-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/11. Policy Gradients and Optimization/.ipynb_checkpoints/11.3 Swinging Up the Pendulum Using DDPG-checkpoint.ipynb -------------------------------------------------------------------------------- /11. Policy Gradients and Optimization/11.2 Lunar Lander Using Policy Gradients.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/11. Policy Gradients and Optimization/11.2 Lunar Lander Using Policy Gradients.ipynb -------------------------------------------------------------------------------- /11. Policy Gradients and Optimization/11.3 Swinging Up the Pendulum Using DDPG.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/11. Policy Gradients and Optimization/11.3 Swinging Up the Pendulum Using DDPG.ipynb -------------------------------------------------------------------------------- /11. Policy Gradients and Optimization/logs/events.out.tfevents.1528712442.sudharsan: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/11. Policy Gradients and Optimization/logs/events.out.tfevents.1528712442.sudharsan -------------------------------------------------------------------------------- /12. Capstone Project: Car Racing using DQN/.ipynb_checkpoints/12.1 Environment Wrapper Functions-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/12. Capstone Project: Car Racing using DQN/.ipynb_checkpoints/12.1 Environment Wrapper Functions-checkpoint.ipynb -------------------------------------------------------------------------------- /12. Capstone Project: Car Racing using DQN/.ipynb_checkpoints/12.2 Dueling network-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/12. Capstone Project: Car Racing using DQN/.ipynb_checkpoints/12.2 Dueling network-checkpoint.ipynb -------------------------------------------------------------------------------- /12. Capstone Project: Car Racing using DQN/.ipynb_checkpoints/12.3 Replay Memory-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/12. Capstone Project: Car Racing using DQN/.ipynb_checkpoints/12.3 Replay Memory-checkpoint.ipynb -------------------------------------------------------------------------------- /12. Capstone Project: Car Racing using DQN/.ipynb_checkpoints/12.4 Training the network-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/12. Capstone Project: Car Racing using DQN/.ipynb_checkpoints/12.4 Training the network-checkpoint.ipynb -------------------------------------------------------------------------------- /12. Capstone Project: Car Racing using DQN/.ipynb_checkpoints/12.5 Car Racing-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/12. Capstone Project: Car Racing using DQN/.ipynb_checkpoints/12.5 Car Racing-checkpoint.ipynb -------------------------------------------------------------------------------- /12. Capstone Project: Car Racing using DQN/12.1 Environment Wrapper Functions.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/12. Capstone Project: Car Racing using DQN/12.1 Environment Wrapper Functions.ipynb -------------------------------------------------------------------------------- /12. Capstone Project: Car Racing using DQN/12.2 Dueling network.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/12. Capstone Project: Car Racing using DQN/12.2 Dueling network.ipynb -------------------------------------------------------------------------------- /12. Capstone Project: Car Racing using DQN/12.3 Replay Memory.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/12. Capstone Project: Car Racing using DQN/12.3 Replay Memory.ipynb -------------------------------------------------------------------------------- /12. Capstone Project: Car Racing using DQN/12.4 Training the network.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/12. Capstone Project: Car Racing using DQN/12.4 Training the network.ipynb -------------------------------------------------------------------------------- /12. Capstone Project: Car Racing using DQN/12.5 Car Racing.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/12. Capstone Project: Car Racing using DQN/12.5 Car Racing.ipynb -------------------------------------------------------------------------------- /13. Recent Advancements and Next Steps/.ipynb_checkpoints/13.3 Deep Q Learning From Demonstrations-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/13. Recent Advancements and Next Steps/.ipynb_checkpoints/13.3 Deep Q Learning From Demonstrations-checkpoint.ipynb -------------------------------------------------------------------------------- /13. Recent Advancements and Next Steps/.ipynb_checkpoints/13.4 Hindsight Experience Replay-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/13. Recent Advancements and Next Steps/.ipynb_checkpoints/13.4 Hindsight Experience Replay-checkpoint.ipynb -------------------------------------------------------------------------------- /13. Recent Advancements and Next Steps/13.3 Deep Q Learning From Demonstrations.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/13. Recent Advancements and Next Steps/13.3 Deep Q Learning From Demonstrations.ipynb -------------------------------------------------------------------------------- /13. Recent Advancements and Next Steps/13.4 Hindsight Experience Replay.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/13. Recent Advancements and Next Steps/13.4 Hindsight Experience Replay.ipynb -------------------------------------------------------------------------------- /13. Recent Advancements and Next Steps/images/B09792_13_01.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/13. Recent Advancements and Next Steps/images/B09792_13_01.png -------------------------------------------------------------------------------- /13. Recent Advancements and Next Steps/images/B09792_13_02.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/13. Recent Advancements and Next Steps/images/B09792_13_02.png -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/README.md -------------------------------------------------------------------------------- /images/Oreilly_safari_logo.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/images/Oreilly_safari_logo.png -------------------------------------------------------------------------------- /images/amazon_logo.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/images/amazon_logo.jpg -------------------------------------------------------------------------------- /images/book_cover.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/images/book_cover.jpg -------------------------------------------------------------------------------- /images/googlebooks_logo.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/images/googlebooks_logo.png -------------------------------------------------------------------------------- /images/googleplay_logo.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/images/googleplay_logo.png -------------------------------------------------------------------------------- /images/packt_logo.jpeg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/images/packt_logo.jpeg -------------------------------------------------------------------------------- /images/packt_logo.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sudharsan13296/Hands-On-Reinforcement-Learning-With-Python/HEAD/images/packt_logo.jpg --------------------------------------------------------------------------------