Research map / Bandits and online learning / Contextual bandits and Thompson sampling
No-Regret Learning in Unknown Games with Correlated Payoffs
Pier Giuseppe Sessa, Ilija Bogunovic, Maryam Kamgarpour, Andreas Krause
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 |
|---|---|---|---|
| Use GP confidence bounds with multiplicative weights and observe opponents' actions | No-regret play in unknown repeated games · Random matrix games, random opponent | time-averaged regret | Improved |
| Use GP confidence bounds with multiplicative weights and observe opponents' actions | No-regret play in unknown repeated games · Random matrix games, GP-MW vs Exp3.P | regret | Improved |
| Use GP confidence bounds with multiplicative weights and observe opponents' actions | No-regret play in unknown repeated games · Sioux-Falls traffic routing | average regret | Improved |
| Use GP confidence bounds with multiplicative weights and observe opponents' actions | No-regret play in unknown repeated games · Sioux-Falls traffic routing | average congestion | Improved |
| Use GP-MW rather than deterministic GP-UCB or StableOpt | Robust Bayesian optimization for MovieLens-100K · MovieLens-100K, random users | average regret | Improved |
| Use GP-MW rather than deterministic GP-UCB or StableOpt | Robust Bayesian optimization for MovieLens-100K · MovieLens-100K, adaptive users | average regret | Improved |
| Provide full-information feedback to Hedge | Random matrix games, random opponent · Random matrix games, random opponent | time-averaged regret | Improved |
Closest papers by meaning
- No Weighted-Regret Learning in Adversarial Bandits with Delays (JMLR 2022 · similarity 0.90)
- Bandit Learning in Concave N-Person Games (NeurIPS 2018 · similarity 0.90)
- Fast and Furious Learning in Zero-Sum Games: Vanishing Regret with Non-Vanishing Step Sizes (NeurIPS 2019 · similarity 0.89)
- Best of Both Worlds: Regret Minimization versus Minimax Play (ICML 2025 · similarity 0.89)
- Principal-Agent Bandit Games with Self-Interested and Exploratory Learning Agents (ICML 2025 · similarity 0.89)
- Mediator Interpretation and Faster Learning Algorithms for Linear Correlated Equilibria in General Sequential Games (ICLR 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.
