Distributed Prioritized Experience Replay

Code

• github.com/vwxyzjn/cleanrl
  pytorch★ 9,383
• github.com/opendilab/DI-engine
  pytorch★ 3,606
• github.com/neka-nat/distributed_rl
  pytorch★ 76
• github.com/Lyusungwon/apex_dqn_pytorch
  pytorch★ 0
• github.com/belepi93/Ape-X
  pytorch★ 0
• github.com/eladsar/rbi
  pytorch★ 0
• github.com/cindycia/Atari-SAC-Discrete
  pytorch★ 0
• github.com/uber-research/ape-x
  tf★ 0
• github.com/HussonnoisMaxence/RL_Algorithms
  pytorch★ 0
• github.com/mightypirate1/DRL-Tetris
  tf★ 0

Abstract

We propose a distributed architecture for deep reinforcement learning at scale, that enables agents to learn effectively from orders of magnitude more data than previously possible. The algorithm decouples acting from learning: the actors interact with their own instances of the environment by selecting actions according to a shared neural network, and accumulate the resulting experience in a shared experience replay memory; the learner replays samples of experience and updates the neural network. The architecture relies on prioritized experience replay to focus only on the most significant data generated by the actors. Our architecture substantially improves the state of the art on the Arcade Learning Environment, achieving better final performance in a fraction of the wall-clock training time.

Tasks

Benchmark Results

Reproductions