English
Related papers

Related papers: Gap-Dependent Bounds for Q-Learning using Referenc…

200 papers

A recent line of works showed regret bounds in reinforcement learning (RL) can be (nearly) independent of planning horizon, a.k.a.~the horizon-free bounds. However, these regret bounds only apply to settings where a polynomial dependency on…

Machine Learning · Computer Science 2024-03-19 Zihan Zhang , Jason D. Lee , Yuxin Chen , Simon S. Du

This paper investigates the challenges of optimal online policy learning under missing data. State-of-the-art algorithms implicitly assume that rewards are always observable. I show that when rewards are missing at random, the Upper…

Econometrics · Economics 2025-07-29 Filippo Palomba

We revisit the reduction of learning in adversarial Markov decision processes [MDPs] to adversarial learning based on $Q$--values; this reduction has been considered in a number of recent articles as one building block to perform policy…

Machine Learning · Computer Science 2025-05-20 Matthieu Jonckheere , Chiara Mignacco , Gilles Stoltz

A crucial problem in reinforcement learning is learning the optimal policy. We study this in tabular infinite-horizon discounted Markov decision processes under the online setting. The existing algorithms either fail to achieve regret…

Machine Learning · Computer Science 2023-12-13 Xiang Ji , Gen Li

To bridge the gap between empirical success and theoretical understanding in transfer reinforcement learning (RL), we study a principled approach with provable performance guarantees. We introduce a novel composite MDP framework where…

Machine Learning · Statistics 2025-02-04 Jinhang Chai , Elynn Chen , Lin Yang

We propose a novel variant of the UCB algorithm (referred to as Efficient-UCB-Variance (EUCBV)) for minimizing cumulative regret in the stochastic multi-armed bandit (MAB) setting. EUCBV incorporates the arm elimination strategy proposed in…

Machine Learning · Computer Science 2018-07-12 Subhojyoti Mukherjee , K. P. Naveen , Nandan Sudarsanam , Balaraman Ravindran

A stochastic combinatorial semi-bandit is an online learning problem where at each step a learning agent chooses a subset of ground items subject to constraints, and then observes stochastic weights of these items and receives their sum as…

Machine Learning · Computer Science 2017-06-08 Branislav Kveton , Zheng Wen , Azin Ashkan , Csaba Szepesvari

We present the first finite time global convergence analysis of policy gradient in the context of infinite horizon average reward Markov decision processes (MDPs). Specifically, we focus on ergodic tabular MDPs with finite state and action…

Machine Learning · Computer Science 2024-03-12 Navdeep Kumar , Yashaswini Murthy , Itai Shufaro , Kfir Y. Levy , R. Srikant , Shie Mannor

This paper presents the first non-asymptotic result showing that a model-free algorithm can achieve a logarithmic cumulative regret for episodic tabular reinforcement learning if there exists a strictly positive sub-optimality gap in the…

Machine Learning · Computer Science 2021-02-24 Kunhe Yang , Lin F. Yang , Simon S. Du

This paper develops a viable notion of learning for sampling-based algorithms that applies in broader settings than previously considered. More specifically, we model a discounted infinite-horizon MDPs with Borel state and action spaces,…

Machine Learning · Statistics 2026-04-09 Daniel Adelman , Cagla Keceli , Alba V. Olivares-Nadal

We study stochastic decision-theoretic online learning with full information and event-level pure differential privacy. A COLT open problem of Hu and Mehta asks to determine the optimal gap-dependent regret rate for stochastic…

Machine Learning · Computer Science 2026-05-29 Tommaso Cesari , Roberto Colomboni

We study regret minimization under privacy constraints in episodic inhomogeneous linear Markov Decision Processes (MDPs), motivated by the growing use of reinforcement learning (RL) in personalized decision-making systems that rely on…

Machine Learning · Computer Science 2025-04-29 Sharan Sahu

We study model-based reinforcement learning with non-linear function approximation where the transition function of the underlying Markov decision process (MDP) is given by a multinomial logistic (MNL) model. We develop a provably efficient…

Machine Learning · Computer Science 2024-10-15 Jaehyun Park , Junyeop Kwon , Dabeen Lee

In this paper, we study the episodic reinforcement learning (RL) problem modeled by finite-horizon Markov Decision Processes (MDPs) with constraint on the number of batches. The multi-batch reinforcement learning framework, where the agent…

Machine Learning · Computer Science 2022-10-18 Zihan Zhang , Yuhang Jiang , Yuan Zhou , Xiangyang Ji

We study model-free Q-learning in finite-horizon episodic Markov Decision Processes (MDPs) with stationary dynamics across episodes. We identify a central issue in nascent model-free posterior-sampling works: the reliance on delayed…

Machine Learning · Computer Science 2026-05-21 Sofia R. Miskala-Dinc , Aviva Prins

We study Markov Decision Processes (MDP) wherein states correspond to causal graphs that stochastically generate rewards. In this setup, the learner's goal is to identify atomic interventions that lead to high rewards by intervening on…

Machine Learning · Computer Science 2021-11-02 Rahul Madhavan , Aurghya Maiti , Gaurav Sinha , Siddharth Barman

A standard assumption in Reinforcement Learning is that the agent observes every visited state-action pair in the associated Markov Decision Process (MDP), along with the per-step rewards. Strong theoretical results are known in this…

Machine Learning · Computer Science 2026-02-03 Zhengjia Zhuo , Anupam Gupta , Viswanath Nagarajan

We introduce learning and planning algorithms for average-reward MDPs, including 1) the first general proven-convergent off-policy model-free control algorithm without reference states, 2) the first proven-convergent off-policy model-free…

Machine Learning · Computer Science 2021-06-29 Yi Wan , Abhishek Naik , Richard S. Sutton

In online learning problems, exploiting low variance plays an important role in obtaining tight performance guarantees yet is challenging because variances are often not known a priori. Recently, considerable progress has been made by Zhang…

Machine Learning · Statistics 2023-02-07 Yeoneung Kim , Insoon Yang , Kwang-Sung Jun

Upper Confidence Bound (UCB) method is arguably the most celebrated one used in online decision making with partial information feedback. Existing techniques for constructing confidence bounds are typically built upon various concentration…

Machine Learning · Statistics 2019-11-01 Botao Hao , Yasin Abbasi-Yadkori , Zheng Wen , Guang Cheng