Similar Items: Pessimism-Free Offline Learning in General-Sum Games via KL Regularization
- Honest Reporting in Scored Oversight: True-KL0 Property via the Prekopa Principle
- Fast Rates in $α$-Potential Games via Regularized Mirror Descent
- Fast Strategy Solving for the Informed Player in Two-Player Zero-Sum Linear-Quadratic Differential Games with One-Sided Information
- Effective, Efficient, and General Information Abstraction for Imperfect-Information Extensive-Form Games
- Knowledge-Free Correlated Agreement for Incentivizing Federated Learning
- Adaptive Liquidity in Prediction Markets via Online Learning