中文
相关论文

相关论文: Evaluating Model-Free Policy Optimization in Maske…

200 篇论文

We study turn-based stochastic zero-sum games with lexicographic preferences over reachability and safety objectives. Stochastic games are standard models in control, verification, and synthesis of stochastic reactive systems that exhibit…

计算机科学与博弈论 · 计算机科学 2022-07-21 Krishnendu Chatterjee , Joost-Pieter Katoen , Maximilian Weininger , Tobias Winkler

Model-based reinforcement learning (MBRL) agents typically learn world models by minimizing predictive loss. However, powerful RL optimizers inevitably exploit minor model inaccuracies, leading to simulator exploitation and a reality gap…

机器学习 · 计算机科学 2026-05-29 Christoph Dann , Yishay Mansour , Mehryar Mohri

We study online learning and equilibrium computation in games with polyhedral decision sets, a property shared by both normal-form games and extensive-form games (EFGs), when the learning agent is restricted to using a best-response oracle.…

计算机科学与博弈论 · 计算机科学 2023-12-07 Darshan Chakrabarti , Gabriele Farina , Christian Kroer

Model-free decentralized optimizations and learning are receiving increasing attention from theoretical and practical perspectives. In particular, two fully decentralized learning algorithms, namely Trial and Error (TEL) and Optimal…

计算机科学与博弈论 · 计算机科学 2017-11-07 Jérôme Gaveau , Christophe J. Le Martret , Mohamad Assaad

We study the problem of finding equilibrium strategies in multi-agent games with incomplete payoff information, where the payoff matrices are only known to the players up to some bounded uncertainty sets. In such games, an ex-post…

计算机科学与博弈论 · 计算机科学 2020-07-14 Wenshuo Guo , Mihaela Curmei , Serena Wang , Benjamin Recht , Michael I. Jordan

Suppose an agent is in a (possibly unknown) Markov Decision Process in the absence of a reward signal, what might we hope that an agent can efficiently learn to do? This work studies a broad class of objectives that are defined solely as…

机器学习 · 计算机科学 2019-01-29 Elad Hazan , Sham M. Kakade , Karan Singh , Abby Van Soest

Zero-sum Markov Games (MGs) has been an efficient framework for multi-agent systems and robust control, wherein a minimax problem is constructed to solve the equilibrium policies. At present, this formulation is well studied under tabular…

机器学习 · 计算机科学 2022-12-06 Yangang Ren , Yao Lyu , Wenxuan Wang , Shengbo Eben Li , Zeyang Li , Jingliang Duan

Reinforcement learning (RL) is a fundamental framework for sequential decision-making, in which an agent learns an optimal policy through interactions with an unknown environment. In settings with function approximation, many existing RL…

机器学习 · 计算机科学 2026-05-05 Ruiquan Huang , Donghao Li , Yingbin Liang , Jing Yang

What is a good exploration strategy for an agent that interacts with an environment in the absence of external rewards? Ideally, we would like to get a policy driving towards a uniform state-action visitation (highly exploring) in a minimum…

机器学习 · 计算机科学 2019-12-20 Mirco Mutti , Marcello Restelli

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…

机器学习 · 计算机科学 2022-07-26 Runyu Zhang , Qinghua Liu , Huan Wang , Caiming Xiong , Na Li , Yu Bai

Multi-task reinforcement learning aims to quickly identify solutions for new tasks with minimal or no additional interaction with the environment. Generalized Policy Improvement (GPI) addresses this by combining a set of base policies to…

机器学习 · 计算机科学 2025-11-14 Lucas N. Alegre , Ana L. C. Bazzan , André Barreto , Bruno C. da Silva

Controllable Markov chains describe the dynamics of sequential decision making tasks and are the central component in optimal control and reinforcement learning. In this work, we give the general form of an optimal policy for learning…

机器学习 · 计算机科学 2025-12-24 Peter N. Loxley

Although multi-agent reinforcement learning can tackle systems of strategically interacting entities, it currently fails in scalability and lacks rigorous convergence guarantees. Crucially, learning in multi-agent systems can become…

多智能体系统 · 计算机科学 2018-03-15 David Mguni , Joel Jennings , Enrique Munoz de Cote

In high stakes environments, agents relying purely on imitation learning or reinforcement learning often struggle to avoid safety-critical errors during exploration. Existing reinforcement learning approaches for environments such as chess…

机器学习 · 计算机科学 2026-03-10 Prajit T Rajendran , Fabio Arnez , Huascar Espinoza , Agnes Delaborde , Chokri Mraidha

We propose a novel independent and payoff-based learning framework for stochastic games that is model-free, game-agnostic, and gradient-free. The learning dynamics follow a best-response-type actor-critic architecture, where agents update…

机器学习 · 计算机科学 2026-02-03 Ahmed Said Donmez , Yuksel Arslantas , Muhammed O. Sayin

We present a new method of blackbox optimization via gradient approximation with the use of structured random orthogonal matrices, providing more accurate estimators than baselines and with provable theoretical guarantees. We show that this…

机器学习 · 计算机科学 2018-06-13 Krzysztof Choromanski , Mark Rowland , Vikas Sindhwani , Richard E. Turner , Adrian Weller

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…

计算机科学与博弈论 · 计算机科学 2022-10-05 Shicong Cen , Yuejie Chi , Simon S. Du , Lin Xiao

Offline reinforcement learning methods typically enforce strict constraints to ensure safety; yet this rigidity often prevents the discovery of optimal behaviors outside the immediate support of the behavior policy. To address this, we…

机器学习 · 计算机科学 2026-05-19 Yifei Chen , Shaoqin Zhu , Xiaoqiang Ji

Multi-agent reinforcement learning (MARL), as a thriving field, explores how multiple agents independently make decisions in a shared dynamic environment. Due to environmental uncertainties, policies in MARL must remain robust to tackle the…

机器学习 · 计算机科学 2025-12-02 Na Li , Zewu Zheng , Wei Ni , Hangguan Shan , Wenjie Zhang , Xinyu Li

This paper studies the problem of data collection for policy evaluation in Markov decision processes (MDPs). In policy evaluation, we are given a target policy and asked to estimate the expected cumulative reward it will obtain in an…

机器学习 · 计算机科学 2022-06-22 Subhojyoti Mukherjee , Josiah P. Hanna , Robert Nowak