Research map / Bandits and online learning / Online convex optimization and games
Learning in Games: Robustness of Fast Convergence
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 learners satisfying Low Approximate Regret with A(d,T)=O(log d) | learning dynamics in smooth games · smooth games with realized feedback | convergence rate to approximate price of anarchy: O(n/T) | Helped |
| use realized feedback instead of expectation feedback | Low Approximate Regret learners · smooth games | feedback information required | Helped |
| use bandit Low Approximate Regret learning | smooth games · bandit feedback | convergence rate to approximate optimality: O(d log T/eps) | Helped |
| use the proposed log-barrier bandit algorithm rather than adaptations of SCRiBLe | bandit learning in smooth games · bandit feedback | dependence on number of actions: O(d log T/eps); O(d^3 log T) | Helped |
| use the proposed log-barrier bandit algorithm instead of GREEN | bandit learning in smooth games · utility maximization settings | applicability: A(d,T)=d log(T/d); A(d,T)=d log(T) | Helped |
| use Noisy Hedge with Low Approximate Regret for shifting experts | dynamic population games · dynamic population games | maximum tolerated turnover probability: p ≤ ε²γ/(κ log(dT)); p ≤ ε²γ²/(κ log(dT)) | Helped |
| use a stable sequence of near-optimal solutions and shifting-expert Low Approximate Regret | learning dynamics in dynamic population games · dynamic population games | average social cost bound: λρ/(1−μ−ε) | Helped |
Closest papers by meaning
- Learning in Markov Games with Adaptive Adversaries: Policy Regret, Fundamental Barriers, and Efficient Algorithms (NeurIPS 2024 · similarity 0.92)
- Optimism Without Regularization: Constant Regret in Zero-Sum Games (NeurIPS 2025 · similarity 0.92)
- No-regret Learning in Harmonic Games: Extrapolation in the Face of Conflicting Interests (NeurIPS 2024 · similarity 0.91)
- Near-Optimal Last-Iterate Convergence for Zero-Sum Games with Bandit Feedback and Opponent Actions (NeurIPS 2026 · similarity 0.91)
- Policy-Regret Minimization in Markov Games with Function Approximation (ICML 2025 · similarity 0.90)
- From Average-Iterate to Last-Iterate Convergence in Games: A Reduction and Its Applications (NeurIPS 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.