用博弈论框架量化信息控制，研究对抗性推理中的认知不确定性。
InfoChess: A Game of Adversarial Inference and a Laboratory for Quantifiable Information Control
- 设计对称对抗游戏，以信息获取为核心目标，无棋子捕获。
- 引入分层启发式智能体与强化学习模型，提升对对手王位的推断准确率。
- 基于信息论指标分析认知不确定性，适合多智能体推理研究者。
我们提出 InfoChess，一种对称的对抗性游戏，将竞争性信息获取设为首要目标。游戏中无棋子捕获，避免物质激励干扰信息作用。棋子用于改变可见性，玩家得分依据其在整个游戏过程中对对手王位位置的概率推断能力。为探索策略空间，我们设计了逐级增强对手建模能力的启发式智能体，并训练出超越基线的强化学习代理。利用游戏的离散结构，我们通过自然的信息论度量分析对局表现，包括信念熵、预言交叉熵及动作诱导观测信道下的预测对数似然。这些指标可分离认知不确定性、校准偏差及对抗移动引发的不确定性。该设计使 InfoChess 成为部分可观测环境下多智能体推理的研究平台。我们开源环境与智能体代码，并提供公共接口以促进进一步研究。
原文摘要 · Abstract (English)
We propose InfoChess, a symmetric adversarial game that elevates competitive information acquisition to the primary objective. There is no piece capture, removing material incentives that would otherwise confound the role of information. Instead, pieces are used to alter visibility. Players are scored on their probabilistic inference of the opponent's king location over the duration of the game. To explore the space of strategies for playing InfoChess, we introduce a hierarchy of heuristic agents defined by increasing levels of opponent modeling, and train a reinforcement learning agent that outperforms these baselines. Leveraging the discrete structure of the game, we analyze gameplay through natural information-theoretic characterizations that include belief entropy, oracle cross entropy, and predictive log score under the action-induced observation channel. These measures disentangle epistemic uncertainty, calibration mismatch, and uncertainty induced by adversarial movement. The design of InfoChess renders it a testbed for studying multi-agent inference under partial observability. We release code for the environment and agents, and a public interface to encourage further study.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。