Massively Parallel Methods for Deep Reinforcement Learning
, , , , , , , , , , , , , and .
(2015)cite arxiv:1507.04296Comment: Presented at the Deep Learning Workshop, International Conference on Machine Learning, Lille, France, 2015.

We present the first massively distributed architecture for deep reinforcement learning. This architecture uses four main components: parallel actors that generate new behaviour; parallel learners that are trained from stored experience; a distributed neural network to represent the value function or behaviour policy; and a distributed store of experience. We used our architecture to implement the Deep Q-Network algorithm (DQN). Our distributed algorithm was applied to 49 games from Atari 2600 games from the Arcade Learning Environment, using identical hyperparameters. Our performance surpassed non-distributed DQN in 41 of the 49 games and also reduced the wall-time required to achieve these results by an order of magnitude on most games.
  • @ross_mck
  • @dblp
  • @jan.hofmann1
This publication has not been reviewed yet.

rating distribution
average user rating0.0 out of 5.0 based on 0 reviews
    Please log in to take part in the discussion (add own reviews or comments).