arXiv Machine Learning
Aug 11
Regret of exploratory policy improvement and $q$-learning
arXiv:2411. 01302v2 Announce Type: replace Abstract: We study the convergence of $q$-learning and related algorithms introduced by Jia and Zhou (J.
Frequency-Uniform Log-Regret Reinforcement Learning for Diffusions
Related stories
arXiv Machine Learning
Sep 22
Provably Efficient Reinforcement Learning in Continuous-Time Episodic MDPs with Poisson Decision Epochs
arXiv:2609. 23127v1 Announce Type: new Abstract: Many real-world reinforcement learning (RL) problems evolve in continuous time, where decisions occur at irregular, event-driven intervals rather than at fixed discrete steps.
arXiv Machine Learning
Aug 3
Convergence and Regret of the Policy Gradient for Multi-Armed Bandits in Diffusion Environment
arXiv:2607. 29593v1 Announce Type: new Abstract: This paper studies the policy gradient update for a multi-arm bandit problem in diffusion environment that is described by a stochastic differential equation (SDE) under the continuous-time reinforcement learning framework by Wang et al.
arXiv Machine Learning
Sep 15
Learning to Solve Stochastic Controls with Unknown Drifts and Running Rewards: Theory, Algorithms and Convergence
The paper investigates continuous‑time stochastic control problems with unknown drift and running reward functions, using an exploratory reinforcement learning framework that incorporates relaxed controls and entropy regularization. It develops policy‑iteration algorithms based on probabilistic representations of the optimal value function and its gradient, proving convergence and demonstrating performance through numerical examples. The study also extends to a special case with control‑dependent diffusion, requiring a Hessian representation.
arXiv AI
Oct 15
Mixing Regularization for Average-Reward $Q$-Learning and $Q$-Planning
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...
arXiv AI
Jun 16
Deep Q-Learning on H\"older Spaces
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 Machine Learning
Oct 9
Closing the Horizon Gap in Policy Optimization for Adversarial MDPs
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.
arXiv Machine Learning
Oct 22
A Model-Free Continuous-Time RL Algorithm from Discrete-Time Off-Policy Data with End-to-End Guarantees
The paper introduces a model‑free continuous‑time reinforcement learning algorithm that learns from a fixed batch of discrete‑time off‑policy data. It builds on the PhiBE‑Q framework to create a PhiBE‑PI policy iteration that uses a single state‑action critic, avoiding explicit drift or diffusion estimation. The authors provide a local end‑to‑end suboptimality guarantee under linear function approximation, analyze error propagation from discretization, function approximation, and finite samples, and reveal a bias‑variance trade‑off where finer time discretization can worsen statistical error.
arXiv Machine Learning
Sep 30
Nonpreemptive Scheduling While Learning Context-Dependent Service Rates
arXiv:2609.37660v1 Announce Type: new Abstract: We study nonpreemptive contextual queueing bandits in a single-server system. Each job is represented by a $d$-dimensional context vector; in each roun...
arXiv Machine Learning
Sep 30
Finite-Sample Theory for Fitted Q-Iteration When Actions Are Functions
arXiv:2609.36390v1 Announce Type: cross Abstract: Offline reinforcement learning seeks optimal decision rules from previously collected data. In some applications, a decision can be an entire functio...
arXiv Machine Learning
Oct 7
Near-Optimal Sample Complexity for Recursive Entropic Risk Reinforcement Learning with a Generative Model
arXiv:2610.06931v1 Announce Type: new Abstract: In this paper, we study the sample complexities of value and policy learning in finite discounted Markov decision processes (MDPs) under recursive entr...
arXiv Machine Learning
Sep 24
Limiting-Kernel Q($\lambda$): Bridging Short and Long Horizons
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.