Reinforcement Learning

Description

This is an implementation of the RL algorithms in Python.

Сurrently implemented algorithms:

1. Q-Learning
2. SARSA
3. Deep Q Network (DQN)
4. Double Deep Q Network (DDQN)
5. Deep Deterministic Policy Gradient (DDPG)
6. Vanilla Policy Gradient (VPG)
7. Advantage Actor Critic (A2C)
8. Proximal Policy Optimization (PPO)

Check out the examples folder for training demonstrations.