RL-Implementation

RL Implementation based on https://github.com/seungeunrho/minimalRL

1. DQN (CartPole) : Playing Atari with Deep Reinforcement Learning
2. DDPG (Pendulum) : Continuous control with deep reinforcement learning
3. TD3 (Pendulum) : Addressing Function Approximation Error in Actor-Critic Methods
4. A3C (CartPole) : Asynchronous Methods for Deep Reinforcement Learning
5. PPO (CartPole) : Proximal Policy Optimization Algorithms

Materials

• 패스트 캠퍼스 [올인원 패키지 : 모델 성능 개선으로 익히는 강화학습 A to Z]

• Policy Gradient Algorithms (official korean translation ver.)