RL

Implemented in Tensorflow 2.x

1. Atari (New_Atari_DQN_image.ipynb, atari_DDDQN.ipynb are correctly implemented but not able to fully train on colab(takes lot of time to train, Will try to get GPU on GCP) )
2. Mountain Car with QLearning (works)
3. Train using qlearning and DeepQLearning (works)
4. Dueling Double Deep Q Learning (works)
5. Deep Q learning (works)
6. ActorCritic (works)
7. Reinforce(Policy Gradient) (works)
8. A2C (works)
9. Multi-Worker_Actor-Critic(A2C) (works)
10. Proximal Policy Optimization (PPO) (works)
11. Deep Deterministic Policy Gradients (DDPG) (works)
12. Twin Delayed Deep Deterministic Policy Gradient (TD3) (works)
13. Soft Actor Critic (softAC) (works, reparameterized sampling not used as of now)

NOTE:- Inside Atari_DQN_image.ipynb, implementation of preprocessing for stacked frame was not correct, so i have uploaded new files with correct implementation.

Recommended resources to learn RL:

1. https://www.coursera.org/specializations/reinforcement-learning (one of the best course for RL fundamentals)
2. https://mitpress.mit.edu/books/reinforcement-learning-second-edition (Book)
3. https://www.youtube.com/channel/UC58v9cLitc8VaCjrcKyAbrw (best for coding)
4. https://adventuresinmachinelearning.com (very useful)
5. https://www.youtube.com/playlist?list=PLWzQK00nc192L7UMJyTmLXaHa3KcO0wBT (Very useful for overview of different algorithms)

   Thanks to:-

6. https://www.youtube.com/channel/UC58v9cLitc8VaCjrcKyAbrw
7. https://www.freecodecamp.org/news/an-introduction-to-deep-q-learning-lets-play-doom-54d02d8017d8/
8. https://rubikscode.net/2019/07/22/deep-convolutional-q-learning-with-python-and-tensorflow-2-0/
9. https://pythonprogramming.net/training-deep-q-learning-dqn-reinforcement-learning-python-tutorial/
10. https://www.packtpub.com/big-data-and-business-intelligence/hands-reinforcement-learning-python
11. http://www0.cs.ucl.ac.uk/staff/D.Silver/web/Teaching.html
12. https://github.com/udacity/deep-reinforcement-learning