Research map / Bandits and online learning / RL theory and MDPs
Learn to Match with No Regret: Reinforcement Learning in Markov Matching Markets
Yifei Min, Tianhao Wang, Ruitu Xu, Zhaoran Wang, Michael Jordan, Zhuoran Yang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| Extend single-step MatchLinUCB to a sequential Markov setting with horizon H | Optimistic RL matching algorithm with linear function approximation · Markov matching market, theoretical analysis | agents' regret bound | Mixed |
| Use d^2-dimensional feature for matching utilities rather than d-dimensional feature | Proposed algorithm · Markov matching market, theoretical analysis | d-dependence of regret bound | No clear effect |
| Bound planner's regret and agents' regret jointly by the sum of optimistic bonuses | Proposed algorithm · Markov matching market, theoretical analysis | total regret | Improved |
Closest papers by meaning
- Decentralized and Uncoordinated Learning of Stable Matchings: A Game-Theoretic Approach (AAAI 2025 · similarity 0.90)
- Improved Bandits in Many-to-One Matching Markets with Incentive Compatibility (AAAI 2024 · similarity 0.89)
- Competing Bandits in Matching Markets via Super Stability (ICML 2025 · similarity 0.89)
- Improved Analysis for Bandit Learning in Matching Markets (NeurIPS 2024 · similarity 0.88)
- Stochastic Matching Bandits with Rare Optimization Updates (NeurIPS 2026 · similarity 0.88)
- Policy-Regret Minimization in Markov Games with Function Approximation (ICML 2025 · similarity 0.87)
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.
