issues
search
facebookresearch
/
rlmeta
RLMeta is a light-weight flexible framework for Distributed Reinforcement Learning Research.
MIT License
284
stars
28
forks
source link
Refactor ReplayBuffer to improve flexibility and performance
#74
Closed
xiaomengy
closed
2 years ago
xiaomengy
commented
2 years ago
This PR made the following changes.
Refactor the design of ReplayBuffer as DeepMind's Reverb project to unify the design of ReplayBuffer and Prioritized Replay Buffer.
Add TensorCircularBuffer to improve the performance of ReplayBuffer with fixed shape tensor data.
Refactor PPO and DQN related implementations.
This PR made the following changes.