English
Related papers

Related papers: Learning Infinite-Horizon Average-Reward Markov De…

200 papers

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 present a new anytime algorithm that achieves near-optimal regret for any instance of finite stochastic partial monitoring. In particular, the new algorithm achieves the minimax regret, within logarithmic factors, for both "easy" and…

Machine Learning · Computer Science 2012-07-03 Gabor Bartok , Navid Zolghadr , Csaba Szepesvari

This paper establishes that optimistic algorithms attain gap-dependent and non-asymptotic logarithmic regret for episodic MDPs. In contrast to prior work, our bounds do not suffer a dependence on diameter-like quantities or ergodicity, and…

Machine Learning · Computer Science 2019-10-30 Max Simchowitz , Kevin Jamieson

We introduce and study constrained Markov Decision Processes (cMDPs) with anytime constraints. An anytime constraint requires the agent to never violate its budget at any point in time, almost surely. Although Markovian policies are no…

Machine Learning · Computer Science 2024-06-14 Jeremy McMahan , Xiaojin Zhu

We study online learning in finite-horizon episodic Markov decision processes (MDPs) under the challenging aggregate bandit feedback model, where the learner observes only the cumulative loss incurred in each episode, rather than individual…

Machine Learning · Computer Science 2025-10-28 Shinji Ito , Kevin Jamieson , Haipeng Luo , Arnab Maiti , Taira Tsuchiya

Existing online learning algorithms for adversarial Markov Decision Processes achieve ${O}(\sqrt{T})$ regret after $T$ rounds of interactions even if the loss functions are chosen arbitrarily by an adversary, with the caveat that the…

Machine Learning · Computer Science 2023-10-27 Tiancheng Jin , Junyan Liu , Chloé Rouyer , William Chang , Chen-Yu Wei , Haipeng Luo

We consider the infinite-horizon linear Markov Decision Processes (MDPs), where the transition probabilities of the dynamic model can be linearly parameterized with the help of a predefined low-dimensional feature mapping. While the…

Machine Learning · Computer Science 2023-10-19 Yu-Heng Hung , Ping-Chun Hsieh , Akshay Mete , P. R. Kumar

We study episodic reinforcement learning with fixed reward and transition functions, but with episode-dependent admissible action sets that are observed at the start of each episode. Performance is measured by cumulative regret against the…

Machine Learning · Computer Science 2026-05-18 Zijun Chen , Zihan Zhang

In this work, we study the low-rank MDPs with adversarially changed losses in the full-information feedback setting. In particular, the unknown transition probability kernel admits a low-rank matrix decomposition \citep{REPUCB22}, and the…

Machine Learning · Computer Science 2023-11-15 Canzhe Zhao , Ruofeng Yang , Baoxiang Wang , Xuezhou Zhang , Shuai Li

We study infinite-horizon Constrained Markov Decision Processes (CMDPs) with general policy parameterizations and multi-layer neural network critics. Existing theoretical analyses for constrained reinforcement learning largely rely on…

Machine Learning · Computer Science 2026-03-10 Anirudh Satheesh , Pankaj Kumar Barman , Washim Uddin Mondal , Vaneet Aggarwal

This paper studies constrained Markov decision processes (CMDPs) with constraints against stochastic thresholds, aiming at safety of reinforcement learning in unknown and uncertain environments. We leverage a Growing-Window estimator…

Machine Learning · Computer Science 2025-12-25 Qian Zuo , Fengxiang He

We study reinforcement learning in infinite-horizon average-reward settings with linear MDPs. Previous work addresses this problem by approximating the average-reward setting by discounted setting and employing a value iteration-based…

Machine Learning · Computer Science 2025-04-17 Kihyuk Hong , Ambuj Tewari

We study the computational complexity of the infinite-horizon discounted-reward Markov Decision Problem (MDP) with a finite state space $|\mathcal{S}|$ and a finite action space $|\mathcal{A}|$. We show that any randomized algorithm needs a…

Computational Complexity · Computer Science 2017-05-24 Yichen Chen , Mengdi Wang

We initiate the study of dynamic regret minimization for goal-oriented reinforcement learning modeled by a non-stationary stochastic shortest path problem with changing cost and transition functions. We start by establishing a lower bound…

Machine Learning · Computer Science 2022-05-27 Liyu Chen , Haipeng Luo

Recent research has revived and amplified interest in algorithms for undiscounted average reward reinforcement learning in infinite-horizon, non-episodic (continuing) tasks. Semi-Markov decision processes (SMDPs) are of particular interest.…

Machine Learning · Computer Science 2026-05-27 Erel Shtossel , Alicia Vidler , Uri Shaham , Gal A. Kaminka

A central issue lying at the heart of online reinforcement learning (RL) is data efficiency. While a number of recent works achieved asymptotically minimal regret in online RL, the optimality of these results is only guaranteed in a…

Machine Learning · Computer Science 2025-04-30 Zihan Zhang , Yuxin Chen , Jason D. Lee , Simon S. Du

We investigate episodic Markov Decision Processes with heavy-tailed losses (HTMDPs). Existing approaches for HTMDPs are conservative in stochastic environments and lack adaptivity in adversarial regimes. In this work, we propose algorithms…

Machine Learning · Computer Science 2026-05-18 Yu Chen , Yuhao Liu , Jiatai Huang , Yihan Du , Longbo Huang

This paper addresses an online convex optimization problem where the cost function at each step depends on a history of past decisions (i.e., memory), and the decision maker has access to limited predictions of future cost values within a…

Optimization and Control · Mathematics 2025-12-29 Zhengmiao Wang , Zhi-Wei Liu , Ming Chi , Xiaoling Wang , Housheng Su , Lintao Ye

It is a remarkable fact that the same $O(\sqrt{T})$ regret rate can be achieved in both the Experts Problem and the Adversarial Multi-Armed Bandit problem albeit with a worse dependence on number of actions in the latter case. In contrast,…

Machine Learning · Computer Science 2022-10-05 Gautam Chandrasekaran , Ambuj Tewari

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