Optimal Learning in Games with Arbitrary Delays: Best-of-Both-Worlds for Self-Play and Adversarial Opponents
cs.LG, stat.ML
Submitted: 2026-11-05
Updated: 2026-11-05
Terminology
Sources
- Constant regret in general games via higher-order optimism
- Linear Convergence in Games with Delayed Feedback via Extra Prediction
- Constant Individual Regret in General Games
- Constant Swap Regret in General-Sum Games via Two-Scale Higher-Order Optimism
- Online Learning: A Modern Introduction Using Convex Optimization
- Universal Online Convex Optimization With Delayed Feedback
- Multiplicative Optimism for Constant Regret in Games
- Near-Optimal Stochastic Linear Bandits with Delay
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis