nosyndicate/policygradient

policy gradient methods implemented using torch

PolicyGradient

Policy Gradient methods implemented using Torch

This project implements some Reinforcement Learning algorithms for continuous control tasks with torch

• REINFORCE
• GPOMDP
• Stochastic Policy Gradient Theorem (SPG)
• Deterministic Policy Gradient Theorem (DPG)
• DGP with Deep Learning (DDPG)
• Deep Continuous Q-Learning

Comments and advice are welcomed!