Is this code only implemented DQN version?

Kaixhin / Rainbow

Rainbow: Combining Improvements in Deep Reinforcement Learning

MIT License

1.56k stars 282 forks source link

Closed JunningHuang closed 6 years ago

JunningHuang commented 6 years ago

Hi, I figure out that this code is only implemented dqn, not ddqn or rainbow. Can you provide a ddqn version for me? Mail: jn8227805@gmail.com

Kaixhin commented 6 years ago

This code currently implements all of the methods listed in Rainbow, which includes relevant changes for the Double Q-learning update here.