English
Related papers

Related papers: On the Sample Complexity of Discounted Reinforceme…

200 papers

While much progress has been made in understanding the minimax sample complexity of reinforcement learning (RL) -- the complexity of learning on the "worst-case" instance -- such measures of complexity often do not capture the true…

Machine Learning · Computer Science 2023-07-21 Andrew Wagenmaker , Kevin Jamieson

We study the problem of learning policies that maximize cumulative reward while satisfying safety constraints, even when the real environment differs from a simulator or nominal model. We focus on robust constrained Markov decision…

Machine Learning · Computer Science 2025-11-12 Sourav Ganguly , Arnob Ghosh

We study reinforcement learning (RL) with linear function approximation. Existing algorithms for this problem only have high-probability regret and/or Probably Approximately Correct (PAC) sample complexity guarantees, which cannot guarantee…

Machine Learning · Computer Science 2022-01-03 Jiafan He , Dongruo Zhou , Quanquan Gu

Several recent works have proposed instance-dependent upper bounds on the number of episodes needed to identify, with probability $1-\delta$, an $\varepsilon$-optimal policy in finite-horizon tabular Markov Decision Processes (MDPs). These…

Machine Learning · Statistics 2023-11-13 Aymen Al-Marjani , Andrea Tirinzoni , Emilie Kaufmann

Binary classification in the classic PAC model exhibits a curious phenomenon: Empirical Risk Minimization (ERM) learners are suboptimal in the realizable case yet optimal in the agnostic case. Roughly speaking, this owes itself to the fact…

Machine Learning · Computer Science 2025-12-22 Julian Asilis , Mikael Møller Høgsgaard , Grigoris Velegkas

We study the problem of agnostic PAC reinforcement learning (RL): given a policy class $\Pi$, how many rounds of interaction with an unknown MDP (with a potentially large state and action space) are required to learn an…

Machine Learning · Computer Science 2023-10-11 Zeyu Jia , Gene Li , Alexander Rakhlin , Ayush Sekhari , Nathan Srebro

Motivated by applications in risk-sensitive reinforcement learning, we study mean-variance optimization in a discounted reward Markov Decision Process (MDP). Specifically, we analyze a Temporal Difference (TD) learning algorithm with linear…

Machine Learning · Computer Science 2025-03-13 Tejaram Sangadi , L. A. Prashanth , Krishna Jagannathan

Safety is a fundamental challenge in reinforcement learning (RL), particularly in real-world applications such as autonomous driving, robotics, and healthcare. To address this, Constrained Markov Decision Processes (CMDPs) are commonly used…

Machine Learning · Computer Science 2026-02-18 Chang Liu , Yunfan Li , Lin F. Yang

Model-free reinforcement learning algorithms combined with value function approximation have recently achieved impressive performance in a variety of application domains. However, the theoretical understanding of such algorithms is limited,…

Machine Learning · Computer Science 2021-02-12 Botao Hao , Nevena Lazic , Yasin Abbasi-Yadkori , Pooria Joulani , Csaba Szepesvari

In safe Reinforcement Learning (RL), safety cost is typically defined as a function dependent on the immediate state and actions. In practice, safety constraints can often be non-Markovian due to the insufficient fidelity of state…

Machine Learning · Computer Science 2024-05-07 Siow Meng Low , Akshat Kumar

We propose risk-sensitive reinforcement learning algorithms catering to three families of risk measures, namely expectiles, utility-based shortfall risk and optimized certainty equivalent risk. For each risk measure, in the context of a…

Machine Learning · Computer Science 2026-02-11 Sumedh Gupte , Shrey Rakeshkumar Patel , Soumen Pachal , Prashanth L. A. , Sanjay P. Bhat

In contrast to the advances in characterizing the sample complexity for solving Markov decision processes (MDPs), the optimal statistical complexity for solving constrained MDPs (CMDPs) remains unknown. We resolve this question by providing…

Machine Learning · Computer Science 2022-11-22 Sharan Vaswani , Lin F. Yang , Csaba Szepesvári

We study the problem of deployment efficient reinforcement learning (RL) with linear function approximation under the \emph{reward-free} exploration setting. This is a well-motivated problem because deploying new policies is costly in…

Machine Learning · Computer Science 2023-02-23 Dan Qiao , Yu-Xiang Wang

We study the sample complexity of reducing reinforcement learning to a sequence of empirical risk minimization problems over the policy space. Such reductions-based algorithms exhibit local convergence in the function space, as opposed to…

Machine Learning · Computer Science 2023-01-26 Naman Agarwal , Brian Bullins , Karan Singh

Statistical performance bounds for reinforcement learning (RL) algorithms can be critical for high-stakes applications like healthcare. This paper introduces a new framework for theoretically measuring the performance of such algorithms…

Machine Learning · Computer Science 2018-01-03 Christoph Dann , Tor Lattimore , Emma Brunskill

Satisfying safety constraints is a priority concern when solving optimal control problems (OCPs). Due to the existence of infeasibility phenomenon, where a constraint-satisfying solution cannot be found, it is necessary to identify a…

Systems and Control · Electrical Eng. & Systems 2026-04-21 Yujie Yang , Zhilong Zheng , Masayoshi Tomizuka , Changliu Liu , Shengbo Eben Li

We study the estimation of risk-sensitive policies in reinforcement learning problems defined by a Markov Decision Process (MDPs) whose state and action spaces are countably finite. Prior efforts are predominately afflicted by computational…

Machine Learning · Statistics 2020-03-02 Junyu Zhang , Amrit Singh Bedi , Mengdi Wang , Alec Koppel

A key challenge in applying reinforcement learning to safety-critical domains is understanding how to balance exploration (needed to attain good performance on the task) with safety (needed to avoid catastrophic failure). Although a growing…

Machine Learning · Computer Science 2021-03-23 Melrose Roderick , Vaishnavh Nagarajan , J. Zico Kolter

We consider the problems of estimation and optimization of two popular convex risk measures: utility-based shortfall risk (UBSR) and Optimized Certainty Equivalent (OCE) risk. We extend these risk measures to cover possibly unbounded random…

Computational Engineering, Finance, and Science · Computer Science 2025-06-03 Sumedh Gupte , Prashanth L. A. , Sanjay P. Bhat

We study a variant of Collaborative PAC Learning, in which we aim to learn an accurate classifier for each of the $n$ data distributions, while minimizing the number of samples drawn from them in total. Unlike in the usual collaborative…

Machine Learning · Computer Science 2024-05-24 Yuyang Deng , Mingda Qiao