Research map / Bandits and online learning / RL theory and MDPs
Provable Self-Play Algorithms for Competitive Reinforcement Learning
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 VI-ULCB, maintaining optimistic and pessimistic value estimates and jointly choosing policies via general-sum equilibria | Zero-sum Markov games · General Markov Game | regret: ˜O(√(H3S2ABT)) | Helped |
| Use reward-free exploration before value iteration and exploitation instead of VI-ULCB throughout play | Zero-sum Markov games · General Markov Game | regret: ˜O((H5S2ABT2)1/3) versus ˜O(√(H3S2ABT)) | Mixed |
| Specialize VI-ULCB to turn-based games | VI-ULCB · Turn-Based Markov Game | regret: ˜O(√(H3S2ABT)) to ˜O(√(H3S2(A + B)T)) | Helped |
| Use mirror descent in the one-step game setting | Zero-sum Markov games · One-step simultaneous game | weak regret: ˜O(√(S(A + B)T)) | Helped |
| Use mirror descent in the two-step turn-based setting | Zero-sum Markov games · Two-step turn-based game | weak regret: ˜O(√(S(A + B)T)) | Helped |
Closest papers by meaning
- Learning Diverse Risk Preferences in Population-Based Self-Play (AAAI 2024 · similarity 0.90)
- GAE Falls Short in Imperfect-Information Self-Play Reinforcement Learning (NeurIPS 2026 · similarity 0.90)
- Provable Memory Efficient Self-Play Algorithm for Model-free Reinforcement Learning (ICLR 2024 · similarity 0.89)
- Convergence of No-Swap-Regret Dynamics in Self-Play (NeurIPS 2024 · similarity 0.88)
- Learning in Markov Games with Adaptive Adversaries: Policy Regret, Fundamental Barriers, and Efficient Algorithms (NeurIPS 2024 · similarity 0.88)
- A Minimaximalist Approach to Reinforcement Learning from Human Feedback (ICML 2024 · 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.