arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2101.02308cs.LG
收藏

分布式多智能体强化学习的编码

Coding for Distributed Multi-Agent Reinforcement Learning

University of California, San Diego(加州大学圣地亚哥分校);San Diego State University(圣地亚哥州立大学)

Baoqian Wang, Junfei Xie, Nikolay Atanasov

摘要:

针对多智能体强化学习(MARL)问题,研究了同步分布式学习中的离散效应。在分布式学习系统中,由于存在各种系统干扰,如计算节点的减速或故障以及通信瓶颈,经常会出现掉队现象。为了解决这个问题,我们提出了一个编码的分布式学习框架,它可以在存在掉队者的情况下加快MARL算法的训练,同时保持与集中式方法相同的准确性。作为一个例子,编码的分布式版本的多代理深度确定性策略梯度(MADDPG)算法的开发和评估。不同的编码方案,包括最大距离可分离(MDS)码,随机稀疏码,基于复制的码,和规则的低密度奇偶检验(LDPC)码也进行了研究。多机器人问题的仿真结果表明,该框架具有良好的性能。

英文摘要:

This paper aims to mitigate straggler effects in synchronous distributed learning for multi-agent reinforcement learning (MARL) problems. Stragglers arise frequently in a distributed learning system, due to the existence of various system disturbances such as slow-downs or failures of compute nodes and communication bottlenecks. To resolve this issue, we propose a coded distributed learning framework, which speeds up the training of MARL algorithms in the presence of stragglers, while maintaining the same accuracy as the centralized approach. As an illustration, a coded distributed version of the multi-agent deep deterministic policy gradient(MADDPG) algorithm is developed and evaluated. Different coding schemes, including maximum distance separable (MDS)code, random sparse code, replication-based code, and regular low density parity check (LDPC) code are also investigated. Simulations in several multi-robot problems demonstrate the promising performance of the proposed framework.

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。

↑