arXiv Machine Learning By Zaiwei Chen, Kaiqing Zhang, Eric Mazumdar, Asuman Ozdaglar, Adam Wierman

Decentralized Best-Response-Based Learning in Two-Player Zero-Sum Stochastic Games: A Finite-Sample Analysis

Read the original on arXiv Machine Learning →

arXiv:2409. 01447v3 Announce Type: replace Abstract: We present a finite-sample analysis of decentralized learning in two-player zero-sum matrix games and stochastic games, with a focus on best-response-based learning algorithms.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning
Jul 17

PAC Learning in Turn-Based Stochastic Games with Reachability Objectives: A Decentralized Private Approach via Expected Conditional Distance

arXiv:2607. 14877v1 Announce Type: new Abstract: Reachability is the most fundamental logical objective, yet it is notoriously difficult to learn in reinforcement learning settings: even for Markov decision processes, PAC learning of reachability is impossible without additional assumptions.

By Ali Asadi, Krishnendu Chatterjee, Pavol Kebis
arXiv AI
Jul 10

Provably Optimal Learning Algorithms for Assistance Games

arXiv:2607. 08012v1 Announce Type: cross Abstract: This paper studies an online variant of the assistance games framework, where an informed agent and an uninformed agent repeatedly interact over $T$ timesteps to optimize a common reward function.

By Nivasini Ananthakrishnan, Mark Bedaywi, Michael I. Jordan, Stuart Russell, Nika Haghtalab
arXiv AI
Jul 14

Efficient Online Proportional Sampling with Applications to Smoothed Online Learning

arXiv:2607. 10963v1 Announce Type: cross Abstract: We study the problem of efficient online proportional sampling from a high-dimensional domain under a $\sigma$-smoothed adversary, where the sampling distribution is induced by a dynamically evolving weight function defined over a sequence of piecewise-structured partitions.

By Amirmahdi Mirfakhar, Maria-Florina Balcan, Hedyeh Beyhaghi
arXiv Machine Learning
Jun 16

Learning Policy from a Single Trajectory in Average-Reward Markov Decision Process

arXiv:2606. 16729v1 Announce Type: new Abstract: While there is an extensive body of work characterizing the sample complexity of discounted cumulative-reward MDPs, finite sample analyses for average-reward MDPs have been limited, and most existing works rely on restrictive assumptions such as ergodicity or access to a generative model.

By Jongmin Lee, Ernest K. Ryu, Vaneet Aggarwal