Reinforcement-Learning

Exploring and implementing different Reinforcement Learning algorithms to better my understanding, particulary model-free control methods.

Value-Based, Policy-Based and Policy-Optimization Methods, and Actor-Critic Methods

TODO

Code Refactoring

1. SARSA, Q-Learning, DQN, Double DQN
2. REINFORCE, REINFORCE with Baseline
3. Advantage Actor-Critic for TD(0)/TD(λ)
4. A2C/A3C
5. TRPO, PPO
6. DDPG, TD3, SAC

Papers Implemented

1. Playing Atari with Deep Reinforcement Learning (DQN)
2. Trust Region Policy Optimization (TRPO)
3. Proximal Policy Optimization (PPO)
4. Generalized Advantage Estimation
5. Continuous Control with Deep Reinforcement Learning (DDPG)
6. Addressing Function Approximation Error in Actor-Critic Methods (TD3)