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.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.
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.
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.
The paper introduces state abstractions that preserve the difference of Q‑functions for offline reinforcement learning, aiming to exclude irrelevant dynamics from rich state data. It proposes a dynamic generalization of the R‑learner that uses orthogonal estimation and sparse learning to estimate the Q‑function contrast, achieving faster convergence and consistency under a margin condition. Experiments on simulated and simulator‑augmented real data show variance reductions and demonstrate that the necessary information for sequential decision‑making can be smaller than that required for full state prediction.
The paper investigates model‑free robust Q‑learning with χ² uncertainty sets and linear function approximation, using data from a single trajectory of an unknown nominal MDP. It introduces a variational reformulation of the robust Bellman target and a blockwise frozen‑target scheme to overcome estimation and non‑contractivity challenges, and proves a finite‑time error bound for every discount factor γ in (0,1). A neural‑network experiment demonstrates the practical use of the variational target in a continuous‑state nonlinear‑control task.
arXiv:2606. 29806v1 Announce Type: cross Abstract: Action-values are foundational to many control algorithms such as Q-learning.
The paper introduces reinforcement learning for Continuous-Time Jump Markov Decision Processes (CTJMDPs) with general discrete state spaces and continuous/discrete actions. It develops entropy‑regularized continuous‑time control and establishes theoretical foundations for q‑learning in this setting, providing model‑free algorithms that outperform naive discretization. Numerical tests on network dynamic pricing demonstrate the method’s ability to learn near‑optimal policies and scale to large networks.