Research map / Bandits and online learning / Online convex optimization and games
Regret Minimization and Convergence to Equilibria in General-sum Markov Games
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use OOMD (optimistic mirror descent with log-barrier) as base algorithm inside swap-regret meta algorithm, instead of FTRL | Policy optimization in Markov games · Theoretical analysis, full-information | regret / path length adaptivity | No clear effect |
| Blocking mechanism (updates only at end of blocks) to get accurate Q estimates in unknown model | Algorithm 1 in unknown dynamics · Unknown model with reachability | swap regret exponent: T^{3/4} -> T^{8/9} | Hurt |
| Independent transition function special case (agents affect only each other's losses) | Algorithm 1 · Full-information independent transitions | individual regret: O(log T) vs Õ(T^{3/4}) | Helped |
Closest papers by meaning
- Policy-Regret Minimization in Markov Games with Function Approximation (ICML 2025 · similarity 0.92)
- Learning Markov Games with Adversarial Opponents: Efficient Algorithms and Fundamental Limits (ICML 2022 · similarity 0.92)
- Hardness of Independent Learning and Sparse Equilibrium Computation in Markov Games (ICML 2023 · similarity 0.92)
- Fast and Furious Learning in Zero-Sum Games: Vanishing Regret with Non-Vanishing Step Sizes (NeurIPS 2019 · similarity 0.92)
- Learning in Markov Games with Adaptive Adversaries: Policy Regret, Fundamental Barriers, and Efficient Algorithms (NeurIPS 2024 · similarity 0.91)
- Near-optimal Regret Using Policy Optimization in Online MDPs with Aggregate Bandit Feedback (ICML 2025 · similarity 0.90)
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.