The paper introduces Dually Regularized AIL, a model‑free algorithm for adversarial imitation learning that jointly applies KL policy regularization and a quadratic reward penalty based on expert and learner occupancies. It proves fast convergence rates, achieving a ×O(1/K+1/N) bound on the regularized imitation gap in finite‑horizon MDPs with general function approximation, and establishes the first algorithm to attain ×O(1/ε) sample complexity in both expert demonstrations and online interactions for this regularized objective.
By Hanbin Zhou, Shangzhe Li, Alexander Braverman, Weitong Zhang
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.
By Donghwan Lee
arXiv:2610.14988v1 Announce Type: cross
Abstract: The average-reward setting for reinforcement learning is challenging because its Bellman operator is known to contract in span only when the underlyi...
By Julien Roger, Sam Bodmer, Jian Qian, Benjamin Riviere
arXiv:2302.07477v4 Announce Type: replace
Abstract: We study the optimal sample complexity of tabular reinforcement learning for infinite-horizon discounted Markov decision processes. The unrestricte...
By Shengbo Wang, Jose Blanchet, Peter Glynn
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.
By Volodymyr Tkachuk, Csaba Szepesv\'ari, Xiaoqi Tan
arXiv:2602. 12107v2 Announce Type: replace-cross Abstract: We study offline reinforcement learning under $Q^\star$-approximation and partial coverage, a setting that motivates practical algorithms such as Conservative $Q$-Learning (CQL; Kumar et al.
By Haolin Liu, Braham Snyder, Chen-Yu Wei
arXiv:2604. 06039v2 Announce Type: replace-cross Abstract: Value iteration-type methods have been extensively studied for computing a nearly optimal value function in reinforcement learning (RL).
By Zhichao Jia, Guanghui Lan
The paper introduces BUMEX, a reinforcement learning exploration strategy that leverages a set of prior models containing the true transition kernel and reward function. By optimizing over this model set, the method derives upper and lower bounds on the Q‑function to guide exploration, providing theoretical guarantees of convergence to the optimal policy. When the model set follows a bounded‑parameter MDP structure, the optimization becomes convex, enabling finite‑time convergence under mild assumptions and demonstrating accelerated learning in simulations.
By J. S. van Hulst, W. P. M. H. Heemels, D. J. Antunes
Limiting‑Kernel Q(λ) (LKQL) is an off‑policy value estimator that blends n‑step truncation with a long‑horizon approximation based on the limiting kernel. It maintains the computational efficiency of n‑step methods while improving policy evaluation accuracy, especially for long‑horizon tasks. The authors prove faster convergence of LKQL’s operator under aperiodicity and near‑on‑policy conditions, and demonstrate empirical gains on MuJoCo continuous‑control benchmarks.
By Tolga Ok, Arman Sharifi Kolarijani, Peyman Mohajerin Esfahani, Mohamad Amin Sharifi Kolarijani
arXiv:2602. 00781v2 Announce Type: replace Abstract: Online reinforcement learning in non-episodic, finite-horizon MDPs remains underexplored and is challenged by the need to estimate returns to a fixed terminal time.
By Jiamin Xu, Kyra Gan
The paper addresses policy optimization in online episodic tabular MDPs with adversarial losses and bandit feedback. By employing regularized Q‑functions, the authors eliminate the extra horizon factor present in previous policy‑optimization regret bounds, achieving high‑probability regret of ≥O(√{HS(H+A)T}) for known transitions and ≥O(HS√{AT}) for unknown transitions. These results improve horizon dependence and match the best-known bounds, with extensions to adversarial linear‑mixture MDPs.
By Mingyi Li, Taira Tsuchiya
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.
By Donghwan Lee