论文标题
使用进化游戏理论进行多代理路径查找
Multi Agent Path Finding using Evolutionary Game Theory
论文作者
论文摘要
在本文中，我们考虑了一组均匀和自主的试剂，以导航以前未知的随机环境。在我们的问题设置中，每个代理商都试图在尊重安全性能的同时最大化给定的效用功能。我们的解决方案是基于进化游戏理论的思想，即复制策略，这些政策效果很好，降低了策略。我们与相关的多基金会计划方法进行了全面的比较，并表明我们的技术在最大程度地降低了RL算法的状态RL算法在大空间中的长度将近30％。我们表明，我们的算法在计算上比Deep RL方法的计算速度更快。我们还表明，与其他方法相比，尤其是路径计划方法相比，代理数量的增加可以更好地缩放。最后，我们从经验上证明，我们学到的政策在进化上是稳定的，因此对任何其他政策都无法入侵。
In this paper, we consider the problem of path finding for a set of homogeneous and autonomous agents navigating a previously unknown stochastic environment. In our problem setting, each agent attempts to maximize a given utility function while respecting safety properties. Our solution is based on ideas from evolutionary game theory, namely replicating policies that perform well and diminishing ones that do not. We do a comprehensive comparison with related multiagent planning methods, and show that our technique beats state of the art RL algorithms in minimizing path length by nearly 30% in large spaces. We show that our algorithm is computationally faster than deep RL methods by at least an order of magnitude. We also show that it scales better with an increase in the number of agents as compared to other methods, path planning methods in particular. Lastly, we empirically prove that the policies that we learn are evolutionarily stable and thus impervious to invasion by any other policy.
