This is a Repository is designed to progress upon the the OpenAI road to being a RL Researcher module link. Along with this, it can also act as a code reference for future aspiring RL researchers. The main algorithms of which the implementation will be added to the repository are as follows-
- Vanilla Policy Gradient- Done
- DQN- Done
- A2C- Done
- PPO
- DDPG
Along with this, the explanation of the algorithm and the concepts of RL has been explained in the PDF. It can be used as an additional reference for a starting point.
Software Requirements-
- Tensorflow
- Gym Environment Openai
- Numpy