English
Related papers

Related papers: Learning Markov Games with Adversarial Opponents: …

200 papers

We investigate a repeated two-player zero-sum game setting where the column player is also a designer of the system, and has full control on the design of the payoff matrix. In addition, the row player uses a no-regret algorithm to…

Computer Science and Game Theory · Computer Science 2023-02-16 Le Cong Dinh , Nick Bishop , Long Tran-Thanh

Deploying autonomous driving systems requires robustness against long-tail scenarios that are rare but safety-critical. While adversarial training offers a promising solution, existing methods typically decouple scenario generation from…

Machine Learning · Computer Science 2026-03-17 Tong Nie , Yihong Tang , Junlin He , Yuewen Mei , Jie Sun , Lijun Sun , Wei Ma , Jian Sun

Policy Space Response Oracle methods (PSRO) provide a general solution to learn Nash equilibrium in two-player zero-sum games but suffer from two drawbacks: (1) the computation inefficiency due to the need for consistent meta-game…

Computer Science and Game Theory · Computer Science 2022-06-02 Ming Zhou , Jingxiao Chen , Ying Wen , Weinan Zhang , Yaodong Yang , Yong Yu , Jun Wang

We consider the use of no-regret algorithms to compute equilibria for particular classes of convex-concave games. While standard regret bounds would lead to convergence rates on the order of $O(T^{-1/2})$, recent work \citep{RS13,SALS15}…

Machine Learning · Computer Science 2018-05-18 Jacob Abernethy , Kevin A. Lai , Kfir Y. Levy , Jun-Kun Wang

We consider learning in an adversarial Markov Decision Process (MDP) where the loss functions can change arbitrarily over $K$ episodes and the state space can be arbitrarily large. We assume that the Q-function of any policy is linear in…

Machine Learning · Computer Science 2023-06-05 Yan Dai , Haipeng Luo , Chen-Yu Wei , Julian Zimmert

We prove that optimistic-follow-the-regularized-leader (OFTRL), together with smooth value updates, finds an $O(T^{-1})$-approximate Nash equilibrium in $T$ iterations for two-player zero-sum Markov games with full information. This…

Machine Learning · Computer Science 2023-02-10 Yuepeng Yang , Cong Ma

We consider the problem of learning by demonstration from agents acting in unknown stochastic Markov environments or games. Our aim is to estimate agent preferences in order to construct improved policies for the same task that the agents…

Machine Learning · Computer Science 2014-08-12 Aristide Tossou , Christos Dimitrakakis

We consider the problem of learning by demonstration from agents acting in unknown stochastic Markov environments or games. Our aim is to estimate agent preferences in order to construct improved policies for the same task that the agents…

Machine Learning · Statistics 2013-07-16 Aristide C. Y. Tossou , Christos Dimitrakakis

A growing line of work reframes preference-based fine-tuning of large language models game-theoretically: Nash Learning from Human Feedback (NLHF) recasts the problem as a zero-sum game over policies. However, optimization is over expected…

Computer Science and Game Theory · Computer Science 2026-05-14 Max Horwitz , Jake Gonzales , Eric Mazumdar , Lillian J. Ratliff

We study distributionally robust Markov games (DR-MGs) with the average-reward criterion, a framework for multi-agent decision-making under uncertainty over extended horizons. In average reward DR-MGs, agents aim to maximize their…

Multiagent Systems · Computer Science 2025-12-12 Zachary Roch , Yue Wang

This paper considers convex games involving multiple agents that aim to minimize their own cost functions using locally available information. A common assumption in the study of such games is that the agents are symmetric, meaning that…

Optimization and Control · Mathematics 2025-09-25 Zifan Wang , Xinlei Yi , Yi Shen , Michael M. Zavlanos , Karl H. Johansson

This work studies an independent natural policy gradient (NPG) algorithm for the multi-agent reinforcement learning problem in Markov potential games. It is shown that, under mild technical assumptions and the introduction of the…

Machine Learning · Computer Science 2023-10-30 Youbang Sun , Tao Liu , Ruida Zhou , P. R. Kumar , Shahin Shahrampour

We revisit the problem of solving two-player zero-sum games in the decentralized setting. We propose a simple algorithmic framework that simultaneously achieves the best rates for honest regret as well as adversarial regret, and in addition…

Computer Science and Game Theory · Computer Science 2018-06-07 Ehsan Asadi Kangarshahi , Ya-Ping Hsieh , Mehmet Fatih Sahin , Volkan Cevher

We study nondeterministic strategies in parity games with the aim of computing a most permissive winning strategy. Following earlier work, we measure permissiveness in terms of the average number/weight of transitions blocked by the…

Logic in Computer Science · Computer Science 2013-01-14 Patricia Bouyer , Nicolas Markey , Jörg Olschewski , Michael Ummels

This brief paper presents simple simulation-based algorithms for obtaining an approximately optimal policy in a given finite set in large finite constrained Markov decision processes. The algorithms are adapted from playing strategies for…

Optimization and Control · Mathematics 2014-12-17 Hyeong Soo Chang

Learning in games provides a powerful framework to design control policies for self-interested agents that may be coupled through their dynamics, costs, or constraints. We consider the case where the dynamics of the coupled system can be…

Systems and Control · Electrical Eng. & Systems 2024-09-18 Mostafa M. Shibl , Vijay Gupta

This paper studies a variant of two-player zero-sum matrix games, where, at each timestep, the row player selects row $i$, the column player selects column $j$, and the row player receives a noisy reward with expected value $A_{i,j}$, along…

Machine Learning · Computer Science 2025-05-27 Arnab Maiti , Kevin Jamieson , Lillian J. Ratliff

Two-player zero-sum games of infinite duration and their quantitative versions are used in verification to model the interaction between a controller (Eve) and its environment (Adam). The question usually addressed is that of the existence…

Computer Science and Game Theory · Computer Science 2021-10-29 Paul Hunter , Guillermo A. Pérez , Jean-François Raskin

It is well-known that for infinitely repeated games, there are computable strategies that have best responses, but no computable best responses. These results were originally proved for either specific games (e.g., Prisoner's dilemma), or…

Computer Science and Game Theory · Computer Science 2020-06-11 Jakub Dargaj , Jakob Grue Simonsen

We consider a policy gradient algorithm applied to a finite-arm bandit problem with Bernoulli rewards. We allow learning rates to depend on the current state of the algorithm, rather than use a deterministic time-decreasing learning rate.…

Machine Learning · Computer Science 2021-09-24 Denis Denisov , Neil Walton
‹ Prev 1 8 9 10 Next ›