Safety
Pessimistic Minimax Learning for Public-Private Information Games under Unilateral Coverage
arXiv:2610.04997v1 Announce Type: new Abstract: We study offline learning in two-player zero-sum contextual games with public and private information, motivated by strategic settings such as auctions
arXiv:2610.04997v1 Announce Type: new Abstract: We study offline learning in two-player zero-sum contextual games with public and private information, motivated by strategic settings such as auctions and negotiations with private valuations. We introduce unilateral prescriptive concentrability and show that asymmetric information can change offline coverage through its effect on equilibrium behavior. For finite state-action spaces, we develop a pessimistic algorithm with an ilde{O}(1/sqrt{n}) exploitability rate, matching the standard sample-size dependence for fully observed minimax games. We further develop a pessimistic policy mirror descent framework, PPA-PMD, for general function approximation and obtain a unified ilde{O}(1/sqrt{n} + 1/sqrt{T}) exploitability rate with no-regret actor updates. Together, these results provide the first theoretical framework for offline equilibrium learning under public-private information constraints.
Related
- Beyond Pessimism: Offline Learning in KL-regularized Games
- Towards Learning Representations of Policies in Two-Player Zero-Sum Imperfect-Information Games
- Minimax-Optimal Policy Regret in Partially Observable Markov Games
Source: arXiv cs.LG | 2026-10-06