Stochastic approximation (SA) is an iterative algorithm to find the fixed point of an operator given noisy samples of this operator. SA appears in many areas such as optimization and …
R Srikant - arXiv preprint arXiv:2401.15719, 2024 - arxiv.org
We prove a non-asymptotic central limit theorem for vector-valued martingale differences using Stein's method, and use Poisson's equation to extend the result to functions of Markov …
Stochastic Approximation (SA) is a widely used algorithmic approach in various fields, including optimization and reinforcement learning (RL). Among RL algorithms, Q-learning is …
Stochastic approximation Markov Chain Monte Carlo (SAMCMC) algorithms are a class of online algorithms having wide-ranging applications, particularly within Markovian systems …
Existing Maximum-Entropy (MaxEnt) Reinforcement Learning (RL) methods for continuous action spaces are typically formulated based on actor-critic frameworks and optimized …
E Anand, G Qu - arXiv preprint arXiv:2403.00222, 2024 - arxiv.org
We study reinforcement learning for global decision-making in the presence of many local agents, where the global decision-maker makes decisions affecting all local agents, and the …
S Wang, J Blanchet, P Glynn - arXiv preprint arXiv:2302.07477, 2023 - arxiv.org
We consider the optimal sample complexity theory of tabular reinforcement learning (RL) for maximizing the infinite horizon discounted reward in a Markov decision process (MDP) …
X Li, Q Sun - arXiv preprint arXiv:2303.05606, 2023 - arxiv.org
This paper presents two algorithms, AdaOFUL and VARA, for online sequential decision- making in the presence of heavy-tailed rewards with only finite variances. For linear …
Two time scale stochastic approximation algorithms emulate singularly perturbed deterministic differential equations in a certain limiting sense, ie, the interpolated iterates on …