Reinforcement Learning Algorithms

Reinforcement Learning solutions for various open-source environments like the OpenAI's Gym Environments.

Algorithms tried so far

• Basic neural networks with state as input and actions as output
• Q-table lookup with (state, action) pairs
• DQN (Deep Q Network)
• DDPG (Deep Deterministic Policy Gradient)

Contributing

Open to enhancements & bug-fixes

Note

The project was made just to try out the OpenAI Gym and some other gym environments. I'm still learning Reinforcement Learning and will try to implement more algorithms and try other environments.