/Reinforcement-Learning-Code

A repository for codes of reinforcement learning algorithms with PyTorch

Primary LanguagePythonMIT LicenseMIT

Reinforcement Learning Code with PyTorch

Papers

Algorithms

01. Model-Free Reinforcement Learning

Deep Q-Network (DQN)

Double DQN (DDQN)

Advantage Actor-Critic (A2C)

Asynchronous Advantage Actor-Critic (A3C)

Deep Deterministic Policy Gradient (DDPG)

Truncated Natural Policy Gradient (TNPG)

Trust Region Policy Optimization (TRPO)

TRPO + Generalized Advantage Estimator (GAE)

Proximal Policy Optimization (PPO)

PPO + Generalized Advantage Estimator (GAE)

Soft Actor-Critic (SAC)

02. Inverse Reinforcement Learning

Apprenticeship Learning via Inverse Reinforcement Learning (APP)

Maximum Entropy Inverse Reinforcement Learning (MaxEnt)

Generative Adversarial Imitation Learning (GAIL)

Variational Adversarial Imitation Learning (VAIL)

Learning curve

CartPole

Pendulum

Hopper

Reference