FastandFuriousLearninginZero-SumGames: VanishingRegretwithNon-VanishingStepSizes

Feb-11-2026, 21:22:18 GMT–Neural Information Processing Systems

This phenomenon, that we coin "fast and furious" learning in games, sets a new benchmark about what is possible both in max-min optimization as well as in multi-agent systems.

artificial intelligence, gradientdescent, machine learning, (14 more...)

Neural Information Processing Systems

Feb-11-2026, 21:22:18 GMT

Conferences PDF

Country:
- North America
  - Canada > British Columbia
    - Metro Vancouver Regional District > Vancouver (0.04)
  - United States
    - California > San Diego County
      - San Diego (0.04)
    - Massachusetts > Middlesex County
      - Cambridge (0.04)
    - Pennsylvania > Philadelphia County
      - Philadelphia (0.04)
    - Texas > Brazos County
      - College Station (0.04)

Technology:
- Information Technology > Artificial Intelligence
  - Machine Learning (0.98)
  - Representation & Reasoning > Agents (1.00)

Duplicate Docs Excel Report

Title
Fast and Furious Learning in Zero-Sum Games: Vanishing Regret with Non-Vanishing Step Sizes

Similar Docs Excel Report more

Title	Similarity	Source
None found