TL;DR
InfoChess is a symmetric adversarial game designed to focus on competitive information acquisition, serving as a testbed for studying multi-agent inference under partial observability.
Contribution
The paper introduces InfoChess, a novel game that isolates information dynamics, along with heuristic and reinforcement learning agents, and provides an information-theoretic analysis framework.
Findings
RL agent outperforms heuristic agents in InfoChess.
Information-theoretic measures effectively analyze gameplay strategies.
Code and environment are publicly released for further research.
Abstract
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
