English
Related papers

Related papers: Pareto Actor-Critic for Equilibrium Selection in M…

200 papers

[Zhang, ICML 2018] provided the first decentralized actor-critic algorithm for multi-agent reinforcement learning (MARL) that offers convergence guarantees. In that work, policies are stochastic and are defined on finite action spaces. We…

Machine Learning · Computer Science 2021-02-22 Antoine Grosnit , Desmond Cai , Laura Wynter

Reinforcement learning, mathematically described by Markov Decision Problems, may be approached either through dynamic programming or policy search. Actor-critic algorithms combine the merits of both approaches by alternating between steps…

Machine Learning · Computer Science 2023-01-31 Harshat Kumar , Alec Koppel , Alejandro Ribeiro

We present a novel, game theoretic representation of a multi-agent prediction market using a partially observable stochastic game with information (POSGI). We then describe a correlated equilibrium (CE)-based solution strategy for this game…

Multiagent Systems · Computer Science 2012-03-28 Janyl Jumadinova , Prithviraj Dasgupta

Autonomous driving (AD) requires safe and reliable decision-making among interacting agents, e.g., vehicles, bicycles, and pedestrians. Multi-agent reinforcement learning (MARL) modeled by Markov games (MGs) provides a suitable framework to…

Systems and Control · Electrical Eng. & Systems 2026-03-20 Huiwen Yan , Mushuang Liu

The application of deep reinforcement learning in multi-agent systems introduces extra challenges. In a scenario with numerous agents, one of the most important concerns currently being addressed is how to develop sufficient collaboration…

Artificial Intelligence · Computer Science 2022-10-12 Bin Zhang , Yunpeng Bai , Zhiwei Xu , Dapeng Li , Guoliang Fan

Reinforcement learning (RL) problems are often phrased in terms of Markov decision processes (MDPs). In this thesis we go beyond MDPs and consider RL in environments that are non-Markovian, non-ergodic and only partially observable. Our…

Artificial Intelligence · Computer Science 2016-11-29 Jan Leike

Cybersecurity defense involves interactions between adversarial parties (namely defenders and hackers), making multi-agent reinforcement learning (MARL) an ideal approach for modeling and learning strategies for these scenarios. This paper…

Multiagent Systems · Computer Science 2025-09-03 Qintong Xie , Edward Koh , Xavier Cadet , Peter Chin

Policy gradient methods in actor-critic reinforcement learning (RL) have become perhaps the most promising approaches to solving continuous optimal control problems. However, the trial-and-error nature of RL and the inherent randomness…

Machine Learning · Computer Science 2024-04-19 Ruofan Wu , Junmin Zhong , Jennie Si

This paper investigates multi-agent reinforcement learning (MARL) in a partially observable, cooperative-competitive combat environment known as LAG. We describe the environment's setup, including agent actions, hierarchical controls, and…

Machine Learning · Computer Science 2025-06-18 Hanzhong Cao

Many real-world domains contain multiple agents behaving strategically with probabilistic transitions and uncertain (potentially infinite) duration. Such settings can be modeled as stochastic games. While algorithms have been developed for…

Computer Science and Game Theory · Computer Science 2020-06-25 Sam Ganzfried , Conner Laughlin , Charles Morefield

Markov games (MGs) provide a mathematical foundation for multi-agent reinforcement learning (MARL), enabling self-interested agents to learn their optimal policies while interacting with others in a shared environment. However, due to the…

Systems and Control · Electrical Eng. & Systems 2025-11-25 Huiwen Yan , Mushuang Liu

Soft Actor-Critic (SAC) is one of the state-of-the-art off-policy reinforcement learning (RL) algorithms that is within the maximum entropy based RL framework. SAC is demonstrated to perform very well in a list of continous control tasks…

Machine Learning · Computer Science 2021-12-22 Zhenyang Shi , Surya P. N. Singh

Multi-agent reinforcement learning (MARL) becomes more challenging in the presence of more agents, as the capacity of the joint state and action spaces grows exponentially in the number of agents. To address such a challenge of scale, we…

Machine Learning · Computer Science 2021-05-19 Yan Li , Lingxiao Wang , Jiachen Yang , Ethan Wang , Zhaoran Wang , Tuo Zhao , Hongyuan Zha

A recently introduced concept of "cooperative equilibrium", based on the assumption that players have a natural attitude to cooperation, has been proven a powerful tool in predicting human behaviour in social dilemmas. In this paper, we…

Computer Science and Game Theory · Computer Science 2015-09-28 Valerio Capraro , Maria Polukarov , Matteo Venanzi , Nicholas R. Jennings

We analyze the distributed power allocation problem in parallel multiple access channels (MAC) by studying an associated non-cooperative game which admits an exact potential. Even though games of this type have been the subject of…

Computer Science and Game Theory · Computer Science 2010-11-29 Panayotis Mertikopoulos , Elena V. Belmega , Aris L. Moustakas , Samson Lasaulce

Multi-agent inverse reinforcement learning (IRL) aims to identify Pareto-efficient behavior in a multi-agent system, and reconstruct utility functions of the individual agents. Motivated by the problem of detecting UAV coordination, how can…

Systems and Control · Electrical Eng. & Systems 2025-09-12 Luke Snow , Vikram Krishnamurthy

A new game theoretical solution concept for open spectrum sharing in cognitive radio (CR) environments is presented, the Lorenz equilibrium (LE). Both Nash and Pareto solution concepts have limitations when applied to real world problems.…

Adaptation and Self-Organizing Systems · Physics 2013-04-08 Ligia Cremene , D. Dumitrescu

This paper studies policy optimization algorithms for multi-agent reinforcement learning. We begin by proposing an algorithm framework for two-player zero-sum Markov Games in the full-information setting, where each iteration consists of a…

Machine Learning · Computer Science 2022-07-26 Runyu Zhang , Qinghua Liu , Huan Wang , Caiming Xiong , Na Li , Yu Bai

We propose WSAC (Weighted Safe Actor-Critic), a novel algorithm for Safe Offline Reinforcement Learning (RL) under functional approximation, which can robustly optimize policies to improve upon an arbitrary reference policy with limited…

Machine Learning · Computer Science 2024-11-01 Honghao Wei , Xiyue Peng , Arnob Ghosh , Xin Liu

Developing reinforcement learning algorithms that satisfy safety constraints is becoming increasingly important in real-world applications. In multi-agent reinforcement learning (MARL) settings, policy optimisation with safety awareness is…

Artificial Intelligence · Computer Science 2022-02-11 Shangding Gu , Jakub Grudzien Kuba , Munning Wen , Ruiqing Chen , Ziyan Wang , Zheng Tian , Jun Wang , Alois Knoll , Yaodong Yang