The paper presents the first PAC learning framework for general-sum concurrent stochastic games with uncertain transitions, addressing the challenge of Nash equilibrium existence. It introduces data‑driven L¹ confidence sets over transition kernels and a robust CSG solver that computes a social‑welfare optimal ε‑NE, or provides a certificate that no exact NE exists. The algorithm achieves polynomial sample complexity under a minimum reachability condition and is validated on benchmark CSGs with near‑optimal performance.
By Angel Y. He, David Parker
arXiv:2610. 01181v1 Announce Type: new Abstract: We consider stochastic games with independent controlled chains and unknown transition kernels, where players observe only their local states and realized payoffs.
By S. Rasoul Etesami
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.
By Zaiwei Chen, Kaiqing Zhang, Eric Mazumdar, Asuman Ozdaglar, Adam Wierman
arXiv:2610.18119v1 Announce Type: cross
Abstract: {\em Specification-Guided Reinforcement Learning (RL)} has largely concerned itself with \emph{learning} an optimal policy against a formal specifica...
By S Akshay, Suguman Bansal, Gaurav Mahla
Robust Markov Decision Processes (RMDPs) generalize classical MDPs by allowing uncertainty in transition probabilities and optimizing against their worst-case realization. We consider $(s,a)$-rectangu...
The paper introduces a sample‑efficient asynchronous Q‑learning algorithm for robust reinforcement learning in infinite‑horizon, discounted robust MDPs with total‑variation uncertainty. It proves that, given a single Markovian trajectory, the algorithm achieves an entrywise ε‑approximation of the optimal Q‑function with a sample complexity bounded by a nearly minimax‑optimal expression involving the discount factor, uncertainty level, mixing time, and occupancy probability. This result improves significantly over prior bounds for robust RL.
By Yuchen Jiao, Gen Li
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:2610.15461v1 Announce Type: new
Abstract: MDP planners often rely on nominal transition models that may differ from the true dynamics. Robust MDP planning accounts for this uncertainty through...
By Tomer Massas, Vadim Indelman
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
arXiv:2606. 14095v1 Announce Type: new Abstract: We study the sample complexity of learning in average-reward weakly-coupled Markov decision processes (WCMDPs) and Restless Bandits (RBs) under a generative model.
By Tianhao Wu, Matthew Zurek, Weina Wang, Qiaomin Xie
arXiv:2607. 17201v1 Announce Type: cross Abstract: In this work we study the Best Policy Identification (BPI) problem in online, tabular Reinforcement Learning.
By Joseph Lazzaro, Alessio Russo, Aldo Pacchiano
arXiv:2610. 08745v1 Announce Type: new Abstract: We study linear bandits under exact sliding-window constraints, where every consecutive block of actions must belong to a prescribed feasible set.
By Seyed Mohammad Hadi Hosseini, Yasin Abbasi-Yadkori, Sattar Vakili