English
Related papers

Related papers: Regret Analysis of Unichain Average Reward Constra…

200 papers

We present the first gap-dependent analysis of regret and communication cost for on-policy federated $Q$-Learning in tabular episodic finite-horizon Markov decision processes (MDPs). Existing FRL methods focus on worst-case scenarios,…

Machine Learning · Statistics 2025-09-19 Haochen Zhang , Zhong Zheng , Lingzhou Xue

We study online learning in constrained Markov decision processes (CMDPs) in which rewards and constraints may be either stochastic or adversarial. In such settings, Stradi et al.(2024) proposed the first best-of-both-worlds algorithm able…

Machine Learning · Computer Science 2025-02-10 Francesco Emanuele Stradi , Anna Lunghi , Matteo Castiglioni , Alberto Marchesi , Nicola Gatti

This paper presents a new model-free algorithm for episodic finite-horizon Markov Decision Processes (MDP), Adaptive Multi-step Bootstrap (AMB), which enjoys a stronger gap-dependent regret bound. The first innovation is to estimate the…

Machine Learning · Computer Science 2021-07-05 Haike Xu , Tengyu Ma , Simon S. Du

We consider a discounted cost constrained Markov decision process (CMDP) policy optimization problem, in which an agent seeks to maximize a discounted cumulative reward subject to a number of constraints on discounted cumulative utilities.…

Optimization and Control · Mathematics 2024-11-21 Sihan Zeng , Thinh T. Doan , Justin Romberg

In this paper, we revisit the regret of undiscounted reinforcement learning in MDPs with a birth and death structure. Specifically, we consider a controlled queue with impatient jobs and the main objective is to optimize a trade-off between…

Machine Learning · Computer Science 2023-02-22 Jonatha Anselmi , Bruno Gaujal , Louis-Sébastien Rebuffi

We analyze the global convergence of the single-timescale actor-critic (AC) algorithm for the infinite-horizon discounted Markov Decision Processes (MDPs) with finite state spaces. To this end, we introduce an elegant analytical framework…

Machine Learning · Computer Science 2025-06-05 Navdeep Kumar , Priyank Agrawal , Giorgia Ramponi , Kfir Yehuda Levy , Shie Mannor

We study the gap-dependent bounds of two important algorithms for on-policy Q-learning for finite-horizon episodic tabular Markov Decision Processes (MDPs): UCB-Advantage (Zhang et al. 2020) and Q-EarlySettled-Advantage (Li et al. 2021).…

Machine Learning · Statistics 2025-03-11 Zhong Zheng , Haochen Zhang , Lingzhou Xue

We study online learning in episodic constrained Markov decision processes (CMDPs), where the learner aims at collecting as much reward as possible over the episodes, while satisfying some long-term constraints during the learning process.…

We propose a framework which generalizes "decision making with structured observations" by allowing robust (i.e. multivalued) models. In this framework, each model associates each decision with a convex set of probability distributions over…

Machine Learning · Computer Science 2025-06-27 Alexander Appel , Vanessa Kosoy

We introduce \texttt{OPO-CMDP}, the first policy optimization algorithm for stochastic Contextual Markov Decision Process (CMDPs) under general offline function approximation. Our approach achieves a high probability regret bound of…

Machine Learning · Computer Science 2026-02-17 Orin Levy , Aviv Rosenberg , Alon Cohen , Yishay Mansour

We propose a novel approach for analyzing dynamic regret of first-order constrained online convex optimization algorithms for strongly convex and Lipschitz-smooth objectives. Crucially, we provide a general analysis that is applicable to a…

Optimization and Control · Mathematics 2025-08-22 Fabian Jakob , Andrea Iannelli

We use the Reward Biased Maximum Likelihood Estimation (RBMLE) algorithm to learn optimal policies for constrained Markov Decision Processes (CMDPs). We analyze the learning regrets of RBMLE.

Optimization and Control · Mathematics 2021-05-31 Rahul Singh

The wide popularity of short videos on social media poses new opportunities and challenges to optimize recommender systems on the video-sharing platforms. Users provide complex and multi-faceted responses towards recommendations, including…

Machine Learning · Computer Science 2022-05-27 Qingpeng Cai , Ruohan Zhan , Chi Zhang , Jie Zheng , Guangwei Ding , Pinghua Gong , Dong Zheng , Peng Jiang

In this paper, we study the problem of (finite horizon tabular) Markov decision processes (MDPs) with heavy-tailed rewards under the constraint of differential privacy (DP). Compared with the previous studies for private reinforcement…

Machine Learning · Computer Science 2023-06-06 Yulian Wu , Xingyu Zhou , Sayak Ray Chowdhury , Di Wang

We consider the task of opportunistic channel access in a primary system composed of independent Gilbert-Elliot channels where the secondary (or opportunistic) user does not dispose of a priori information regarding the statistical…

Machine Learning · Statistics 2009-08-04 Sarah Filippi , Olivier Cappé , Aurélien Garivier

Many real-world applications, such as those in medical domains, recommendation systems, etc, can be formulated as large state space reinforcement learning problems with only a small budget of the number of policy changes, i.e., low…

Machine Learning · Computer Science 2021-01-05 Minbo Gao , Tianle Xie , Simon S. Du , Lin F. Yang

The standard assumption in reinforcement learning (RL) is that agents observe feedback for their actions immediately. However, in practice feedback is often observed in delay. This paper studies online learning in episodic Markov decision…

Machine Learning · Computer Science 2023-01-24 Tiancheng Jin , Tal Lancewicki , Haipeng Luo , Yishay Mansour , Aviv Rosenberg

We consider reinforcement learning (RL) in episodic Markov decision processes (MDPs) with linear function approximation under drifting environment. Specifically, both the reward and state transition functions can evolve over time but their…

Machine Learning · Computer Science 2024-04-16 Huozhi Zhou , Jinglin Chen , Lav R. Varshney , Ashish Jagmohan

We study the reinforcement learning problem in the setting of finite-horizon episodic Markov Decision Processes (MDPs) with $S$ states, $A$ actions, and episode length $H$. We propose a model-free algorithm UCB-Advantage and prove that it…

Machine Learning · Computer Science 2020-06-09 Zihan Zhang , Yuan Zhou , Xiangyang Ji

We study risk-sensitive reinforcement learning (RL) based on an entropic risk measure in episodic non-stationary Markov decision processes (MDPs). Both the reward functions and the state transition kernels are unknown and allowed to vary…

Machine Learning · Computer Science 2022-11-22 Yuhao Ding , Ming Jin , Javad Lavaei