Junhojuno / Lets-RL

Reinforcement Learning with Pytorch :joy:

Lets-RL

Reinforcement Learning myself 😂

Silver Lecture 정리

• Introduction
• Markov Decision Process
• Planning by DP
• Model-Free Prediction
• Model-Free Control
• Function Approximation
• Policy Gradient
• Model-Based RL

논문 리뷰

Value-Based RL

• DQN : Playing Atari with Deep Reinforcement Learning
• Double DQN : Deep Reinforcement Learning with Double Q-learning
• PER : Prioritized Experience Replay
• Dueling Network

Policy-Based RL

• TRPO : Trust Region Policy Optimization
• PPO : Proximal Policy Optimization
• DPG : Deterministic Policy Gradient Algorithms
• DDPG : Continuous Control with Deep Reinforcement Learning
• TD3 : Addressing Function Approximation Error in Actor-Critic Methods

코드 with Pytorch

• Cartpole
  • DQN
• MountainCar
  • DQN
  • Double DQN
  • Prioritized Expereiences Replay
  • Dueling Network