首页/论文/1102.1580

arXiv 1102.15802011-02-08cs.GT

部分可观测蒙特卡罗树搜索的多重树

Multiple Tree for Partially Observable Monte-Carlo Tree Search

David Auger

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

摘要英文摘要相关论文

摘要：

基于最近的Bandit方法，我们提出了一个用蒙特卡罗树搜索计算部分可观察博弈近似纳什均衡的算法。我们得到的实验结果的游戏幻影井字棋，表明强的战略，可以有效地计算我们的算法。

英文摘要：

We propose an algorithm for computing approximate Nash equilibria of partially observable games using Monte-Carlo tree search based on recent bandit methods. We obtain experimental results for the game of phantom tic-tac-toe, showing that strong strategies can be efficiently computed by our algorithm.

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。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

摘要英文摘要相关论文

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。

继续探索

相关论文

单边部分可观测追逃对策的动态规划

Dynamic Programming for One-Sided Partially Observable Pursuit-Evasion Games

追逐-逃避场景广泛出现在机器人、安全领域和许多其他现实世界的情况中。我们专注于两个球员的追求-逃避游戏，同时移动，无限的地平线，和折扣奖励。我们假设参与者具有部分可观察性，然而，逃避者被赋予了知道追击者单位当前位置的优势。此设置对于安全域特别有意义，在这些安全域中，通常需要一个健壮的策略，旨在最大化最坏情况下的效用。我们提供了，据我们所知，第一个算法，证明收敛到一个部分可观察的追求-逃避游戏的价值与无限的地平线。我们的算法扩展了著名的价值迭代算法，利用（1）我们的游戏的价值函数只依赖于位置的追求者和他的信念，他对当前位置的逃避者，（2）这些功能是分段线性和凸的信念空间。

2016-08-04cs.GT

Compact Representation of Value Function in Partially Observable Stochastic Games

Value methods for solving stochastic games with partial observability model the uncertainty about states of the game as a probability distribution over possible states. The dimension of this belief space is the number of states. For many practical problems, for example in security, there are exponentially many possible states which causes an insufficient scalability of algorithms for real-world problems. To this end, we propose an abstraction technique that addresses this issue of the curse of dimensionality by projecting high-dimensional beliefs to characteristic vectors of significantly lowe…

2019-03-13cs.GT

弥合部分可观测随机博弈与稀疏 POMDP 方法之间的差距

Bridging the Gap between Partially Observable Stochastic Games and Sparse POMDP Methods

提出融合 POMDP 信念近似与信息集博弈均衡搜索的统一框架，从理论上界定近似误差并通过数值示例验证，以支持大状态空间 POSG 规划。

2024-10-28cs.GT

The Partially Observable History Process

University of Alberta（阿尔伯塔大学）；Amii（Amii（阿尔伯塔机器智能研究所））；Brown University（布朗大学）

We introduce the partially observable history process (POHP) formalism for reinforcement learning. POHP centers around the actions and observations of a single agent and abstracts away the presence of other players without reducing them to stochastic processes. Our formalism provides a streamlined interface for designing algorithms that defy categorization as exclusively single or multi-agent, and for developing theory that applies across these domains. We show how the POHP formalism unifies traditional models including the Markov decision process, the Markov game, the extensive-form game, and…

2022-02-24cs.AIcs.GT

不完美感知下的移动目标搜索：一种部分可观测随机博弈论方法

Mobile Target Search with Imperfect Perception: A Partially Observable Stochastic Game Theoretical Approach

Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University（同济大学上海自主智能无人系统科学中心）；Department of Control Science and Engineering, Tongji University（同济大学控制科学与工程系）

针对传感器限制、恶意干扰或通信噪声导致的不完美感知，采用部分可观测随机博弈（POSG）框架建模搜索者与目标间的对抗互动，提出可检测性概念和基于随机递归分析的充分判据，并开发服务器辅助分布式算法。

2026-06-19cs.GTcs.RO

Partially Observable Games for Secure Autonomy

California Institute of Technology（加州理工学院）；Jet Propulsion Laboratory, California Institute of Technology（加州理工学院喷气推进实验室）

Technology development efforts in autonomy and cyber-defense have been evolving independently of each other, over the past decade. In this paper, we report our ongoing effort to integrate these two presently distinct areas into a single framework. To this end, we propose the two-player partially observable stochastic game formalism to capture both high-level autonomous mission planning under uncertainty and adversarial decision making subject to imperfect information. We show that synthesizing sub-optimal strategies for such games is possible under finite-memory assumptions for both the autono…

2020-02-05cs.AIcs.CRcs.FL

更多相关论文收起更多论文

基于HSVI的带神经感知机制的部分可观测随机博弈在线极小极大策略

HSVI-based Online Minimax Strategies for Partially Observable Stochastic Games with Neural Perception Mechanisms

Department of Computer Science, University of Oxford（牛津大学计算机科学系）；School of Computing Science, University of Glasgow（格拉斯哥大学计算科学学院）

针对带神经感知机制的非对称信息部分可观测随机博弈，首次提出基于HSVI的在线ε-极小极大策略求解方法，通过持续求解与推断信念策略，仅需单线性规划即可高效求解。

2024-04-16cs.AIcs.GT

具有神经感知机制的部分可观测随机博弈

Partially Observable Stochastic Games with Neural Perception Mechanisms

University of Oxford（牛津大学）；University of Glasgow（格拉斯哥大学）

本文提出神经符号部分可观测随机博弈模型及单边NS-HSVI求解方法，利用神经网络原像分析和粒子信念表示，验证了其在行人-车辆与追逃场景中的实用性。

2024-06-30cs.GTcs.LG

部分可观测多智能体强化学习与信息共享

Partially Observable Multi-Agent Reinforcement Learning with Information Sharing

本文研究了在部分可观测随机游戏框架下可证明的多智能体强化学习问题，提出利用智能体间的信息共享来解决计算复杂性问题，并设计了具有准多项式时间复杂度的算法，扩展至合作部分可观测马尔可夫决策过程。

2026-03-12cs.GTcs.LGcs.MA

Secure Control in Partially Observable Environments to Satisfy LTL Specifications

This paper studies the synthesis of control policies for an agent that has to satisfy a temporal logic specification in a partially observable environment, in the presence of an adversary. The interaction of the agent (defender) with the adversary is modeled as a partially observable stochastic game. The goal is to generate a defender policy to maximize satisfaction of a given temporal logic specification under any adversary policy. The search for policies is limited to the space of finite state controllers, which leads to a tractable approach to determine policies. We relate the satisfaction …

2020-11-05cs.CRcs.GTcs.LO

Actor-Critic Policy Optimization in Partially Observable Multiagent Environments

DeepMind（深度思考公司）

Optimization of parameterized policies for reinforcement learning (RL) is an important and challenging problem in artificial intelligence. Among the most common approaches are algorithms based on gradient ascent of a score function representing discounted return. In this paper, we examine the role of these policy gradient and actor-critic algorithms in partially-observable multiagent environments. We show several candidate policy update rules and relate them to a foundation of regret minimization and multiagent learning techniques for the one-shot and tabular cases, leading to previously unkno…

2020-06-12cs.AIcs.GTcs.LG

部分可观测轨迹博弈的在线竞争性信息收集

Online Competitive Information Gathering for Partially Observable Trajectory Games

Vanderbilt University（范德比大学）

本文针对部分可观测随机博弈中连续规划难处理的问题，提出一种基于粒子估计与随机梯度博弈的在线轨迹规划方法，在追逃和仓库场景中验证其能实现主动信息收集并优于被动方法。

2025-06-02cs.AIcs.GTcs.MA

Sample-Efficient Reinforcement Learning of Partially Observable Markov Games

Princeton University（普林斯顿大学）；DeepMind（深度思维）；University of Alberta（阿尔伯塔大学）

This paper considers the challenging tasks of Multi-Agent Reinforcement Learning (MARL) under partial observability, where each agent only sees her own individual observations and actions that reveal incomplete information about the underlying state of system. This paper studies these tasks under the general model of multiplayer general-sum Partially Observable Markov Games (POMGs), which is significantly larger than the standard model of Imperfect Information Extensive-Form Games (IIEFGs). We identify a rich subclass of POMGs -- weakly revealing POMGs -- in which sample-efficient learning is …

2022-10-17cs.AIcs.GTcs.LG