arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1802.00899cs.MAcs.GTcs.LGmath.OC
收藏

马尔可夫势博弈的参数闭环策略学习

Learning Parametric Closed-Loop Policies for Markov Potential Games

Information Processing and Telecommunications Center(信息处理与电信中心);Universidad Politécnica de Madrid(马德里理工大学)

Sergio Valcarcel Macua, Javier Zazo, Santiago Zazo

摘要:

在多智能体系统中,智能体之间相互作用,并与随机环境可以形式化为随机游戏。我们研究了一个子类命名为马尔可夫势博弈(MPGs),经常出现在经济和工程应用中的代理人共享一个共同的资源。我们认为MPG连续状态动作变量,耦合约束和非凸奖励。以前的分析遵循变分方法,仅适用于非常简单的情况(凸奖励,可逆动态,没有耦合约束);或考虑确定性动态,并提供开环(OL)分析,研究策略,包括预定义的动作序列,这不是最佳的随机环境。我们提出了一个闭环(CL)分析MPG和考虑参数的政策,取决于当前的状态。我们为随机博弈是MPG提供了易于验证的充分必要条件,即使对于复杂的参数函数(例如,深度神经网络);并表明闭环纳什均衡(NE)可以通过求解相关的最优控制问题(OCP)来找到(或至少近似)。这是有用的,因为解决一个OCP-这是一个单目标问题-通常比解决形成游戏的耦合OCP的原始集合要简单得多-这是一个多目标控制问题。这是一个相当大的改进,以前的标准方法的CL分析的MPG,没有近似的解决方案,如果没有NE属于所选择的参数家庭,这是实际的,只有简单的参数形式。我们用一个例子说明了我们的方法来非合作通信工程游戏的理论贡献。然后,我们用深度强化学习算法来解决这个游戏,该算法学习的策略非常接近游戏的精确变分NE。

英文摘要:

Multiagent systems where agents interact among themselves and with a stochastic environment can be formalized as stochastic games. We study a subclass named Markov potential games (MPGs) that appear often in economic and engineering applications when the agents share a common resource. We consider MPGs with continuous state-action variables, coupled constraints and nonconvex rewards. Previous analysis followed a variational approach that is only valid for very simple cases (convex rewards, invertible dynamics, and no coupled constraints); or considered deterministic dynamics and provided open-loop (OL) analysis, studying strategies that consist in predefined action sequences, which are not optimal for stochastic environments. We present a closed-loop (CL) analysis for MPGs and consider parametric policies that depend on the current state. We provide easily verifiable, sufficient and necessary conditions for a stochastic game to be an MPG, even for complex parametric functions (e.g., deep neural networks); and show that a closed-loop Nash equilibrium (NE) can be found (or at least approximated) by solving a related optimal control problem (OCP). This is useful since solving an OCP--which is a single-objective problem--is usually much simpler than solving the original set of coupled OCPs that form the game--which is a multiobjective control problem. This is a considerable improvement over the previously standard approach for the CL analysis of MPGs, which gives no approximate solution if no NE belongs to the chosen parametric family, and which is practical only for simple parametric forms. We illustrate the theoretical contributions with an example by applying our approach to a noncooperative communications engineering game. We then solve the game with a deep reinforcement learning algorithm that learns policies that closely approximates an exact variational NE of the game.

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。

↑