arXiv:2607. 22399v1 Announce Type: cross Abstract: We consider the problem of learning from a single finite trajectory of an ergodic stochastic dynamical system.
Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.
arXiv:2607. 23502v1 Announce Type: cross Abstract: We study empirical risk minimization for learning non-linear dynamical systems whose transition dynamics may switch over time.
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.
arXiv:2606. 18183v1 Announce Type: cross Abstract: Temporal difference (TD) learning with linear function approximation is a core method for policy evaluation.
arXiv:2603. 23461v2 Announce Type: replace Abstract: We study reinforcement learning (RL) with linear function approximation in Markov Decision Processes (MDPs) satisfying \emph{linear Bellman completeness} -- a fundamental setting where the Bellman backup of any linear value function remains linear.
We consider the problem of sampling compositional and discrete objects from a given unnormalized posterior distribution. Notably, recent studies have shown that this problem can be efficiently solved by learning a deterministic Markov Decision Process (MDP) that progressively builds each object in proportion to the posterior.
arXiv:2510. 03494v2 Announce Type: replace Abstract: We study finite-horizon offline reinforcement learning (RL) with function approximation for both policy evaluation and policy optimization.