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 2105.07933cs.MAcs.AI
收藏

平均场游戏群!强化学习方法

Mean Field Games Flock! The Reinforcement Learning Way

Univ. Lille(里尔大学);CNRS(法国国家科学研究中心);Inria(法国国家信息与自动化研究所);Centrale Lille(里尔中央理工学院);Princeton University(普林斯顿大学);DeepMind Paris(巴黎深度思维);Google Research(谷歌研究院)

Sarah Perrin, Mathieu Laurière, Julien Pérolat, Matthieu Geist, Romuald Élie, Olivier Pietquin

摘要:

我们提出了一种方法,使大量的代理人学习如何羊群,这是一个自然的行为,在大规模的动物种群。这个问题已经引起了很多人的兴趣,但需要许多结构性假设,并且仅在小维度上易于处理。我们把这个问题称为平均场博弈(MFG),其中每个个体根据群体行为选择其加速度。结合深度强化学习(RL)和规范化流(NF),我们获得了一个易于处理的解决方案,只需要非常弱的假设。我们的算法找到了一个纳什均衡和代理适应他们的速度,以匹配相邻羊群的平均。我们使用Fictionary Play和交替:(1)使用Deep RL计算近似最佳响应,(2)使用NF估计下一个群体分布。我们数值表明,我们的算法学习多组或高维群集的障碍。

英文摘要:

We present a method enabling a large number of agents to learn how to flock, which is a natural behavior observed in large populations of animals. This problem has drawn a lot of interest but requires many structural assumptions and is tractable only in small dimensions. We phrase this problem as a Mean Field Game (MFG), where each individual chooses its acceleration depending on the population behavior. Combining Deep Reinforcement Learning (RL) and Normalizing Flows (NF), we obtain a tractable solution requiring only very weak assumptions. Our algorithm finds a Nash Equilibrium and the agents adapt their velocity to match the neighboring flock's average one. We use Fictitious Play and alternate: (1) computing an approximate best response with Deep RL, and (2) estimating the next population distribution with NF. We show numerically that our algorithm learn multi-group or high-dimensional flocking with obstacles.

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。

↑