Refactor Ape-X DQN Agent

facebookresearch / rlmeta

RLMeta is a light-weight flexible framework for Distributed Reinforcement Learning Research.

MIT License

284 stars 28 forks source link

Closed xiaomengy closed 1 year ago

xiaomengy commented 1 year ago

This PR refactors Ape-X DQN agent to clean up code. It also make the arguments in PPO Agents to be aligned with DQN.