English
Related papers

Related papers: Internal State-Based Policy Gradient Methods for P…

200 papers

Solving partially observable Markov decision processes (POMDPs) is highly intractable in general, at least in part because the optimal policy may be infinitely large. In this paper, we explore the problem of finding the optimal policy from…

Artificial Intelligence · Computer Science 2013-01-30 Nicolas Meuleau , Kee-Eung Kim , Leslie Pack Kaelbling , Anthony R. Cassandra

We contribute the first provable guarantees of global convergence to Nash equilibria (NE) in two-player zero-sum convex Markov games (cMGs) by using independent policy gradient methods. Convex Markov games, recently defined by Gemp et al.…

Computer Science and Game Theory · Computer Science 2025-06-23 Fivos Kalogiannis , Emmanouil-Vasileios Vlatakis-Gkaragkounis , Ian Gemp , Georgios Piliouras

We study infinite-horizon discounted two-player zero-sum Markov games, and develop a decentralized algorithm that provably converges to the set of Nash equilibria under self-play. Our algorithm is based on running an Optimistic Gradient…

Machine Learning · Computer Science 2021-07-08 Chen-Yu Wei , Chung-Wei Lee , Mengxiao Zhang , Haipeng Luo

In this paper, we consider a large class of constrained non-cooperative stochastic Markov games with countable state spaces and discounted cost criteria. In one-player case, i.e., constrained discounted Markov decision models, it is…

Optimization and Control · Mathematics 2021-12-16 Anna Jaśkiewicz , Andrzej S. Nowak

This paper studies the synthesis of control policies for an agent that has to satisfy a temporal logic specification in a partially observable environment, in the presence of an adversary. The interaction of the agent (defender) with the…

Systems and Control · Computer Science 2019-03-19 Bhaskar Ramasubramanian , Andrew Clark , Linda Bushnell , Radha Poovendran

Game theoretic methods have become popular for planning and prediction in situations involving rich multi-agent interactions. However, these methods often assume the existence of a single local Nash equilibria and are hence unable to handle…

Computer Science and Game Theory · Computer Science 2023-05-24 Oswin So , Paul Drews , Thomas Balch , Velin Dimitrov , Guy Rosman , Evangelos A. Theodorou

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

In this paper, we investigate the mean field games with $K$ classes of agents who are weakly coupled via the empirical measure. The underlying dynamics of the representative agents is assumed to be a controlled nonlinear Markov process…

Probability · Mathematics 2012-04-09 Vassili N. Kolokoltsov , Jiajie Li , Wei Yang

The recent mean field game (MFG) formalism facilitates otherwise intractable computation of approximate Nash equilibria in many-agent settings. In this paper, we consider discrete-time finite MFGs subject to finite-horizon objectives. We…

Multiagent Systems · Computer Science 2022-07-11 Kai Cui , Heinz Koeppl

We study data-driven learning of robust stochastic control for infinite-horizon systems with potentially continuous state and action spaces. In many managerial settings--supply chains, finance, manufacturing, services, and dynamic…

Machine Learning · Statistics 2025-11-18 Shengbo Wang , Jason Meng , Nian Si , Jose Blanchet , Zhengyuan Zhou

We study the problem of learning a Nash equilibrium (NE) in Markov games which is a cornerstone in multi-agent reinforcement learning (MARL). In particular, we focus on infinite-horizon adversarial team Markov games (ATMGs) in which agents…

Computer Science and Game Theory · Computer Science 2024-10-10 Fivos Kalogiannis , Jingming Yan , Ioannis Panageas

Traditional multi-agent reinforcement learning algorithms are not scalable to environments with more than a few agents, since these algorithms are exponential in the number of agents. Recent research has introduced successful methods to…

Multiagent Systems · Computer Science 2021-01-26 Sriram Ganapathi Subramanian , Matthew E. Taylor , Mark Crowley , Pascal Poupart

In this paper, we consider reinforcement learning of Markov Decision Processes (MDP) with peak constraints, where an agent chooses a policy to optimize an objective and at the same time satisfy additional constraints. The agent has to take…

Optimization and Control · Mathematics 2019-12-09 Ather Gattami

We study what dataset assumption permits solving offline two-player zero-sum Markov games. In stark contrast to the offline single-agent Markov decision process, we show that the single strategy concentration assumption is insufficient for…

Machine Learning · Computer Science 2022-10-17 Qiwen Cui , Simon S. Du

We study provable multi-agent reinforcement learning (RL) in the general framework of partially observable stochastic games (POSGs). To circumvent the known hardness results and the use of computationally intractable oracles, we advocate…

Machine Learning · Computer Science 2026-03-16 Xiangyu Liu , Kaiqing Zhang

We consider a class of two-player dynamic stochastic nonzero-sum games where the state transition and observation equations are linear, and the primitive random variables are Gaussian. Each controller acquires possibly different dynamic…

Systems and Control · Computer Science 2014-01-21 Abhishek Gupta , Ashutosh Nayyar , Cedric Langbort , Tamer Basar

Multi-Agent Reinforcement Learning (MARL) -- where multiple agents learn to interact in a shared dynamic environment -- permeates across a wide range of critical applications. While there has been substantial progress on understanding the…

Computer Science and Game Theory · Computer Science 2022-10-05 Shicong Cen , Yuejie Chi , Simon S. Du , Lin Xiao

First order kinetic mean field games formally describe the Nash equilibria of deterministic differential games where agents control their acceleration, asymptotically in the limit as the number of agents tends to infinity. The known results…

Analysis of PDEs · Mathematics 2022-07-12 Megan Griffin-Pickering , Alpár R. Mészáros

Markov games (MGs) and multi-agent reinforcement learning (MARL) are studied to model decision making in multi-agent systems. Traditionally, the objective in MG and MARL has been risk-neutral, i.e., agents are assumed to optimize a…

Computer Science and Game Theory · Computer Science 2024-06-11 Hafez Ghaemi , Shirin Jamshidi , Mohammad Mashreghi , Majid Nili Ahmadabadi , Hamed Kebriaei

Multi-agent reinforcement learning (MARL) lies at the heart of a plethora of applications involving the interaction of a group of agents in a shared unknown environment. A prominent framework for studying MARL is Markov games, with the goal…

Machine Learning · Computer Science 2025-02-17 Tong Yang , Bo Dai , Lin Xiao , Yuejie Chi