arXiv:2606. 16846v1 Announce Type: cross Abstract: We study the operator-theoretic core of Q-learning in continuous-time stochastic control with continuous states and actions.
arXiv:2607. 08340v1 Announce Type: cross Abstract: Q-learning is a fundamental algorithm in reinforcement learning (RL) for solving discounted Markov decision processes (MDPs) when the transition kernel is unknown.
arXiv:2606. 29806v1 Announce Type: cross Abstract: Action-values are foundational to many control algorithms such as Q-learning.
arXiv:2608. 14401v1 Announce Type: cross Abstract: In offline RL, estimating the optimal action-value function $Q^*$ can be formulated as solving the optimal Bellman equation based solely on offline observations.
arXiv:2601. 22970v2 Announce Type: replace-cross Abstract: Policies learned via continuous actor-critic methods often exhibit erratic, high-frequency oscillations, making them unsuitable for physical deployment.
arXiv:2511. 03836v2 Announce Type: replace Abstract: Deep Q-Networks (DQNs) estimate future returns by learning from transitions sampled from a replay buffer.
arXiv:2506. 13862v2 Announce Type: replace-cross Abstract: In Reinforcement Learning (RL), regularization with a Kullback-Leibler divergence that penalizes large deviations between successive policies has emerged as a popular tool both in theory and practice.
arXiv:2411. 01302v2 Announce Type: replace Abstract: We study the convergence of $q$-learning and related algorithms introduced by Jia and Zhou (J.
arXiv:2606. 02645v1 Announce Type: cross Abstract: Periodic target updates in Q-learning and soft target updates in actor-critic methods are empirically well established stabilization mechanisms, but their precise theoretical explanation is still incomplete.
arXiv:2605. 16103v2 Announce Type: replace Abstract: Q-learning is known to suffer from overestimation bias: because the Bellman update maximizes noisy or imperfect action-value estimates, positive errors can be selected and propagated, causing learned values to exceed the true optimal values.
arXiv:2506. 07040v4 Announce Type: replace-cross Abstract: We study model-free methods for distributionally robust infinite-horizon average-reward Markov decision processes (MDPs).
arXiv:2606. 10835v1 Announce Type: cross Abstract: Periodic hard target updates are among the most common stabilization devices in modern deep Q-learning.
arXiv:2605. 28276v2 Announce Type: replace Abstract: Reinforcement learning algorithms are commonly analyzed (and designed) under the Markov assumption.