SuReLI / Pytorch-RL-Agents

Our implementations of a few RL algo with Pytorch

Pytorch-RL-Agents

A few RL algorithms implemented by SuReLI with Pytorch.

Algorithms

• DDPG : Deep Deterministic Policy Gradient presented in Continuous control with deep reinforcement learning.

• DQN : Deep Q-Network presented in Playing Atari with Deep Reinforcement Learning

• SAC : Soft Actor-Critic presented in Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor

• TD3 : Twin Delayed Deep Deterministic policy gradient Addressing Function Approximation Error in Actor-Critic Methods

Requirements

• Pytorch
• gym
• (Optionnal) roboschool
• tensorboardX