English
Related papers

Related papers: Provably Efficient Fictitious Play Policy Optimiza…

200 papers

Self-play reinforcement learning has demonstrated significant success in learning complex strategic and interactive behaviors in competitive multi-agent games. However, achieving such behaviors in continuous decision spaces remains…

Machine Learning · Computer Science 2025-11-18 Akash Karthikeyan , Yash Vardhan Pant

We make significant progress toward the stochastic shortest path problem with adversarial costs and unknown transition. Specifically, we develop algorithms that achieve $\widetilde{O}(\sqrt{S^2ADT_\star K})$ regret for the full-information…

Machine Learning · Computer Science 2021-06-15 Liyu Chen , Haipeng Luo

Reinforcement learning has solid foundations, but becomes inefficient in partially observed (non-Markovian) environments. Thus, a learning agent -born with a representation and a policy- might wish to investigate to what extent the Markov…

Artificial Intelligence · Computer Science 2011-03-02 Gabor Matuz , Andras Lorincz

Policy regret is a well established notion of measuring the performance of an online learning algorithm against an adaptive adversary. We study restrictions on the adversary that enable efficient minimization of the \emph{complete policy…

Machine Learning · Statistics 2022-04-26 Dhruv Malik , Yuanzhi Li , Aarti Singh

In this paper, we propose a new efficient algorithm to compute the value function for zero-sum stopping games featuring two players with opposing interests. This can be seen as a game version of the ''forward algorithm'' for (one-player)…

Probability · Mathematics 2026-02-03 Nhat-Thang Le

We introduce DREAM, a deep reinforcement learning algorithm that finds optimal strategies in imperfect-information games with multiple agents. Formally, DREAM converges to a Nash Equilibrium in two-player zero-sum games and to an…

Machine Learning · Computer Science 2020-12-01 Eric Steinberger , Adam Lerer , Noam Brown

In this paper, we study mechanism design for single-facility location games where each agent has multiple private locations in [0, 1]. The individual objective is a satisfaction function that measures the discrepancy between the optimal…

Computer Science and Game Theory · Computer Science 2025-12-30 Huanjun Wang , Qizhi Fang , Wenjing Liu

We consider two agents playing simultaneously the same stochastic three-armed bandit problem. The two agents are cooperating but they cannot communicate. We propose a strategy with no collisions at all between the players (with very high…

Computer Science and Game Theory · Computer Science 2020-07-13 Sébastien Bubeck , Thomas Budzinski

We study minimax optimal reinforcement learning in episodic factored Markov decision processes (FMDPs), which are MDPs with conditionally independent transition components. Assuming the factorization is known, we propose two model-based…

Machine Learning · Computer Science 2020-06-25 Yi Tian , Jian Qian , Suvrit Sra

A recent goal in the Reinforcement Learning (RL) framework is to choose a sequence of actions or a policy to maximize the reward collected or minimize the regret incurred in a finite time horizon. For several RL problems in operation…

Machine Learning · Computer Science 2016-08-18 K J Prabuchandran , Tejas Bodas , Theja Tulabandhula

We extend anytime constraints to the Markov game setting and the corresponding solution concept of an anytime-constrained equilibrium (ACE). Then, we present a comprehensive theory of anytime-constrained equilibria that includes (1) a…

Machine Learning · Computer Science 2025-03-05 Jeremy McMahan

This paper presents new families of algorithms for the repeated play of two-agent (near) zero-sum games and two-agent zero-sum stochastic games. For example, the family includes fictitious play and its variants as members. Commonly, the…

Computer Science and Game Theory · Computer Science 2023-11-03 Yuksel Arslantas , Ege Yuceel , Yigit Yalin , Muhammed O. Sayin

We study agents communicating over an underlying network by exchanging messages, in order to optimize their individual regret in a common nonstochastic multi-armed bandit problem. We derive regret minimization algorithms that guarantee for…

Machine Learning · Computer Science 2019-11-19 Yogev Bar-On , Yishay Mansour

Recent results of Ye and Hansen, Miltersen and Zwick show that policy iteration for one or two player (perfect information) zero-sum stochastic games, restricted to instances with a fixed discount rate, is strongly polynomial. We show that…

Optimization and Control · Mathematics 2013-10-21 Marianne Akian , Stéphane Gaubert

We present a method to automatically find security strategies for the use case of intrusion prevention. Following this method, we model the interaction between an attacker and a defender as a Markov game and let attack and defense…

Machine Learning · Computer Science 2024-04-23 Kim Hammar , Rolf Stadler

The combination of Monte-Carlo Tree Search (MCTS) and deep reinforcement learning is state-of-the-art in two-player perfect-information games. In this paper, we describe a search algorithm that uses a variant of MCTS which we enhanced by 1)…

Machine Learning · Computer Science 2020-05-26 Arta Seify , Michael Buro

Optimization under uncertainty is a fundamental problem in learning and decision-making, particularly in multi-agent systems. Previously, Feldman, Kalai, and Tennenholtz [2010] demonstrated the ability to efficiently compete in repeated…

Computer Science and Game Theory · Computer Science 2026-01-29 Daniel Ablin , Alon Cohen

We consider an N-player multi-armed bandit game where each player chooses one out of M arms for T turns. Each player has different expected rewards for the arms, and the instantaneous rewards are independent and identically distributed or…

Computer Science and Game Theory · Computer Science 2021-04-06 Ilai Bistritz , Amir Leshem

Regret matching (RM) -- and its modern variants -- is a foundational online algorithm that has been at the heart of many AI breakthrough results in solving benchmark zero-sum games, such as poker. Yet, surprisingly little is known so far in…

Computer Science and Game Theory · Computer Science 2025-11-18 Ioannis Anagnostides , Emanuel Tewolde , Brian Hu Zhang , Ioannis Panageas , Vincent Conitzer , Tuomas Sandholm

Finding numerical approximations to minimax regret treatment rules is of key interest. To do so when potential outcomes are in {0,1} we discretize the action space of nature and apply a variant of Robinson's (1951) algorithm for iterative…

Econometrics · Economics 2025-03-17 Patrik Guggenberger , Jiaqi Huang
‹ Prev 1 8 9 10 Next ›