Research map / Learning theory and algorithms / Submodular and game algorithms
Payoff-Only Learning in Games via Best-Response Differential Inclusions
Ismail Hassan, Pedro G Lind, Anis Yazidi
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Analyzes an epochal payoff-only learning recursion for finite normal-form games, where each player uses only its own realized rewards and steps toward an empirical near-best vertex of a barrier simplex.
Problem
Learning in finite normal-form games when each player observes only its own realized reward, with opponents' actions and payoffs unknown.
Approach
An epochal recursion holds the mixed strategy fixed over long epochs, estimates own-action means from bandit data, and moves toward an empirical near-best vertex of a barrier simplex; the stochastic recursion is reduced to a best-response differential inclusion.
Closest papers by meaning
- No Coin Left Behind: Maximizing Strategic Surplus Against No-Regret Dynamics (NeurIPS 2026 · similarity 0.89)
- Near-Optimal Last-Iterate Convergence for Zero-Sum Games with Bandit Feedback and Opponent Actions (NeurIPS 2026 · similarity 0.89)
- No-regret Learning in Harmonic Games: Extrapolation in the Face of Conflicting Interests (NeurIPS 2024 · similarity 0.89)
- Fast Last-Iterate Convergence of Learning in Games Requires Forgetful Algorithms (NeurIPS 2024 · similarity 0.88)
- From Average-Iterate to Last-Iterate Convergence in Games: A Reduction and Its Applications (NeurIPS 2025 · similarity 0.88)
- The Harder Path: Last Iterate Convergence for Uncoupled Learning in Zero-Sum Games with Bandit Feedback (ICML 2025 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
