arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 0812.1599cs.MAcs.AI
收藏

多智能体强化学习与遗传策略共享

Multi-Agent Reinforcement Learning and Genetic Policy Sharing

Clark University(克拉克大学)

Jake Ellowitz

摘要:

在多智能体动力系统中,智能体之间的策略共享的影响还没有得到广泛的研究。我模拟了一个使用强化学习优化同一任务的代理系统,以研究不同人口密度和策略共享的影响。我证明了共享政策减少了达到渐近行为的时间,并导致改进的渐近行为。

英文摘要:

The effects of policy sharing between agents in a multi-agent dynamical system has not been studied extensively. I simulate a system of agents optimizing the same task using reinforcement learning, to study the effects of different population densities and policy sharing. I demonstrate that sharing policies decreases the time to reach asymptotic behavior, and results in improved asymptotic behavior.

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。

↑