paper-with-me

홈 › Papers

Repeated Games against Budgeted Adversaries

2010-12-01 · NeurIPS 2010 12 · Jacob D. Abernethy, Manfred K. Warmuth

We study repeated zero-sum games against an adversary on a budget. Given that an adversary has some constraint on the sequence of actions that he plays, we consider what ought to be the player's best mixed strategy with knowledge of this budget. We show that, for a general class of normal-form games, the minimax strategy is indeed efficiently computable and relies on a random playout" technique. We give three diverse applications of this algorithmic template: a cost-sensitive "Hedge" setting, a particular problem in Metrical Task Systems, and the design of combinatorial prediction markets."

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Predicting Dynamic Difficulty

2011-12-01 · NeurIPS 2011 12 · Olana Missura, Thomas Gärtner

Motivated by applications in electronic games as well as teaching systems, we investigate the problem of dynamic difficulty adjustment. The task here is to repeatedly find a game difficulty setting that is neither `too e…

Reducing Exploitability with Population Based Training

2022-08-10 · Pavel Czempin, Adam Gleave

Self-play reinforcement learning has achieved state-of-the-art, and often superhuman, performance in a variety of zero-sum games. Yet prior work has found that policies that are highly capable against regular opponents c…

Diversity

SPIKE: An Adaptive Dual Controller Framework for Cost-Efficient Long-Horizon Game Agents

2026-05-18 · Wencan Jiang, Jiangning Zhang, Jianbiao Mei, Jinzhuo Liu 외 arxiv

Long-horizon multimodal agents in open-world games must stay goal-directed across many low-level interactions under tight token and latency budgets. Existing approaches often trade off costly per-step reasoning against r…

Learning in Markov Games with Adaptive Adversaries: Policy Regret, Fundamental Barriers, and Efficient Algorithms

2024-11-01 · Thanh Nguyen-Tang, Raman Arora

We study learning in a dynamically evolving environment modeled as a Markov game between a learner and a strategic opponent that can adapt to the learner's strategies. While most existing works in Markov games focus on e…

counterfactual

Foolproof Cooperative Learning

2019-06-24 · Alexis Jacq, Julien Perolat, Matthieu Geist, Olivier Pietquin

This paper extends the notion of learning equilibrium in game theory from matrix games to stochastic games. We introduce Foolproof Cooperative Learning (FCL), an algorithm that converges to a Tit-for-Tat behavior. It all…