Research map / Reinforcement learning / MDPs and planning
Pessimistic Minimax Value Iteration: Provably Efficient Equilibrium Learning from Offline Datasets
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 pessimistic and optimistic value estimates with uncertainty bonuses, then solve the associated matrix-game Nash equilibria | PMVI · Offline linear Markov games | suboptimality: 4\beta \cdot \ri(\cD, x) | Helped |
| Require low relative uncertainty, covering policy pairs that hold one equilibrium policy fixed while varying the opponent | Offline linear Markov games · Offline linear Markov games | sample efficiency: c'd^{3/2}H^2K^{-1/2}\sqrt{\zeta} | Helped |
| Use dataset coverage only over the Nash equilibrium policy pair | Offline equilibrium learning · Offline linear Markov games | suboptimality: 2 | Hurt |
Closest papers by meaning
- Offline Learning in Markov Games with General Function Approximation (ICML 2023 · similarity 0.93)
- Learning Equilibria in Adversarial Team Markov Games: A Nonconvex-Hidden-Concave Min-Max Optimization Problem (NeurIPS 2024 · similarity 0.91)
- Optimistic Policy Gradient in Multi-Player Markov Games with a Single Controller: Convergence beyond the Minty Property (AAAI 2024 · similarity 0.91)
- Improving Sample Efficiency of Model-Free Algorithms for Zero-Sum Markov Games (ICML 2024 · similarity 0.90)
- Solving Zero-Sum Convex Markov Games (ICML 2025 · similarity 0.90)
- Fast Last-Iterate Convergence of Learning in Games Requires Forgetful Algorithms (NeurIPS 2024 · similarity 0.89)
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.