Distributed Prioritized Experience Replay

ICLR 2018 Dan HorganJohn QuanDavid BuddenGabriel Barth-MaronMatteo HesselHado van HasseltDavid Silver

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... (read more)

PDF Abstract

Evaluation results from the paper

Task Dataset Model Metric name Metric value Global rank Compare
Atari Games Atari-57 Ape-X Medium Human-Normalized Score 434.1% # 1