The paper introduces Quasar, a model‑free Q‑learning algorithm that guarantees asymptotic convergence for reachability objectives in Markov Decision Processes that are free of non‑terminal maximal end components (MECs). Unlike prior model‑based methods, Quasar does not estimate transition probabilities, reducing memory usage from O(|S|²|A|) to O(|S||A|). Experiments on the Quantitative Verification Benchmark Set show that Quasar converges to optimal policies with far fewer samples than existing state‑of‑the‑art model‑based approaches.
By Lu-Chin Chang, Suguman Bansal
arXiv:2512. 14617v2 Announce Type: replace-cross Abstract: Many practical decision-making problems involve tasks whose success depends on the entire system history, rather than on achieving a state with desired properties.
By Alessandro Trapasso, Luca Iocchi, Fabio Patrizi
arXiv:2607. 01197v1 Announce Type: new Abstract: Quantum computing has emerged as a promising computational paradigm for machine learning (ML), with the potential to offer computational advantages over classical approaches.
By Chuanming Yu, Jiaming Liu, Zihao Ge, Xiongfei Wu, Lulu Zhu, Pengzhan Zhao, Jianjun Zhao
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
arXiv:2607. 10694v1 Announce Type: cross Abstract: We study the problem of optimal continual fine-tuning for a pre-trained Foundation Model deployed at a resource-limited device.
By Thomas Tsouparopoulos, Iordanis Koutsopoulos
arXiv:2607. 10959v1 Announce Type: new Abstract: Standard learning rate schedules such as cosine annealing are tied to a fixed training horizon, limiting their ability to accommodate post hoc horizon extension.
By Jianhao Ma, Yuxin Chen
arXiv:2608. 02826v1 Announce Type: cross Abstract: Reinforcement learning is a subfield of machine learning that studies how an agent interacts with an environment in order to extract as large a reward as possible.
By Joao F. Doriguello
In this work, we consider decision-focused learning (DFL) for a Markov decision process (MDP), where existing methods differentiate through the KKT conditions of the Bellman equation and require solvi...
arXiv:2510. 06647v2 Announce Type: replace-cross Abstract: We study fine-grained gap-dependent regret bounds for model-free reinforcement learning in episodic tabular Markov Decision Processes.
By Haochen Zhang, Zhong Zheng, Lingzhou Xue
arXiv:2606. 18503v1 Announce Type: new Abstract: Remaining useful life (RUL) estimation is central to predictive maintenance, where an unplanned failure can cost far more than the asset itself.
By Manoranjan Gandhudi, Arunkumar V., G. R. Anil, Gangadharan G. R
arXiv:2507. 22854v3 Announce Type: replace-cross Abstract: We propose novel classical and quantum online algorithms for learning finite- and infinite-horizon Markov Decision Processes (MDPs).
By Andris Ambainis, Joao F. Doriguello, Debbie Lim
arXiv:2606. 30358v1 Announce Type: cross Abstract: We design an algorithm for learning the coefficients of an $n$-qubit constant-local Lindbladian to $\varepsilon$ error with $O(g d^2 \log(n) / \varepsilon^2)$ total evolution time, where $g$ is the single-site energy and $d$ is the (approximate) degree of the interaction graph.
By Laura Lewis, Ewin Tang, John Wright