G-Wang / RL-Experiments

Implementations of deep reinforcement learning algorithms for experiments

RL-Experiments

The motivation of this project is to compare and modify deep reinforcement learning algorithms easily for experiments. So it is not highly modularized.

Implemented algorithms

• DQN
• TRPO

Dependency

Tested in macOS 10.13

• Python 2.7.10
• OpenAI gym 0.10.3
• PyTorch 0.3.0