深度强化学习的大规模并行方法
Massively Parallel Methods for Deep Reinforcement Learning
摘要：
我们提出了第一个用于深度强化学习的大规模分布式架构。该架构使用四个主要组件：生成新行为的并行演员;从存储的经验中训练的并行学习者;表示价值函数或行为策略的分布式神经网络;以及分布式经验存储。我们使用我们的架构来实现深度Q网络算法（DQN）。我们的分布式算法被应用到49个游戏从雅达利2600游戏的街机学习环境，使用相同的超参数。我们的性能在49款游戏中的41款中超过了非分布式DQN，并且在大多数游戏中减少了实现这些结果所需的墙时间。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
