English
Related papers

Related papers: Tackling Heavy-Tailed Rewards in Reinforcement Lea…

200 papers

In this paper, we study risk-sensitive Reinforcement Learning (RL), focusing on the objective of Conditional Value at Risk (CVaR) with risk tolerance $\tau$. Starting with multi-arm bandits (MABs), we show the minimax CVaR regret rate is…

Machine Learning · Computer Science 2023-05-26 Kaiwen Wang , Nathan Kallus , Wen Sun

Value function approximation has demonstrated phenomenal empirical success in reinforcement learning (RL). Nevertheless, despite a handful of recent progress on developing theory for RL with linear function approximation, the understanding…

Machine Learning · Computer Science 2020-06-22 Ruosong Wang , Ruslan Salakhutdinov , Lin F. Yang

The batched multi-armed bandit (MAB) problem, in which rewards are collected in batches, is crucial for applications such as clinical trials. Existing research predominantly assumes light-tailed reward distributions, yet many real-world…

Machine Learning · Computer Science 2026-03-24 Yunwen Guo , Yunlun Shu , Gongyi Zhuo , Tianyu Wang

For the problem of task-agnostic reinforcement learning (RL), an agent first collects samples from an unknown environment without the supervision of reward signals, then is revealed with a reward and is asked to compute a corresponding…

Machine Learning · Computer Science 2022-03-16 Jingfeng Wu , Vladimir Braverman , Lin F. Yang

State-of-the-art efficient model-based Reinforcement Learning (RL) algorithms typically act by iteratively solving empirical models, i.e., by performing \emph{full-planning} on Markov Decision Processes (MDPs) built by the gathered…

Machine Learning · Computer Science 2019-11-01 Yonathan Efroni , Nadav Merlis , Mohammad Ghavamzadeh , Shie Mannor

We study online reinforcement learning for finite-horizon deterministic control systems with {\it arbitrary} state and action spaces. Suppose that the transition dynamics and reward function is unknown, but the state and action space is…

Machine Learning · Computer Science 2019-05-07 Lin F. Yang , Chengzhuo Ni , Mengdi Wang

We study finite-armed semiparametric bandits, where each arm's reward combines a linear component with an unknown, potentially adversarial shift. This model strictly generalizes classical linear bandits and reflects complexities common in…

Machine Learning · Statistics 2025-06-18 Seok-Jin Kim , Gi-Soo Kim , Min-hwan Oh

Switching costs, which capture the costs for changing policies, are regarded as a critical metric in reinforcement learning (RL), in addition to the standard metric of losses (or rewards). However, existing studies on switching costs (with…

Machine Learning · Computer Science 2023-02-10 Ming Shi , Yingbin Liang , Ness Shroff

Modern Reinforcement Learning (RL) is commonly applied to practical problems with an enormous number of states, where function approximation must be deployed to approximate either the value function or the policy. The introduction of…

Machine Learning · Computer Science 2019-08-09 Chi Jin , Zhuoran Yang , Zhaoran Wang , Michael I. Jordan

The success of reinforcement learning (RL) crucially depends on effective function approximation when dealing with complex ground-truth models. Existing sample-efficient RL algorithms primarily employ three approaches to function…

Machine Learning · Computer Science 2024-01-09 Yunfan Li , Lin Yang

Contextual bandit with linear reward functions is among one of the most extensively studied models in bandit and online learning research. Recently, there has been increasing interest in designing \emph{locally private} linear contextual…

Machine Learning · Statistics 2024-04-16 Jiachun Li , David Simchi-Levi , Yining Wang

We study the reinforcement learning (RL) problem in a constrained Markov decision process (CMDP), where an agent explores the environment to maximize the expected cumulative reward while satisfying a single constraint on the expected total…

This paper studies model-based bandit and reinforcement learning (RL) with nonlinear function approximations. We propose to study convergence to approximate local maxima because we show that global convergence is statistically intractable…

Machine Learning · Computer Science 2022-08-04 Kefan Dong , Jiaqi Yang , Tengyu Ma

In this study, we propose a new method for constructing UCB-type algorithms for stochastic multi-armed bandits based on general convex optimization methods with an inexact oracle. We derive the regret bounds corresponding to the convergence…

Machine Learning · Computer Science 2024-02-13 Yuriy Dorn , Aleksandr Katrutsa , Ilgam Latypov , Andrey Pudovikov

Learning from human feedback plays an important role in aligning generative models, such as large language models (LLM). However, the effectiveness of this approach can be influenced by adversaries, who may intentionally provide misleading…

Machine Learning · Computer Science 2025-11-13 Qiwei Di , Jiafan He , Quanquan Gu

We consider learning in an adversarial Markov Decision Process (MDP) where the loss functions can change arbitrarily over $K$ episodes and the state space can be arbitrarily large. We assume that the Q-function of any policy is linear in…

Machine Learning · Computer Science 2023-06-05 Yan Dai , Haipeng Luo , Chen-Yu Wei , Julian Zimmert

In this paper, we study multi-armed bandits (MAB) and stochastic linear bandits (SLB) with heavy-tailed rewards and quantum reward oracle. Unlike the previous work on quantum bandits that assumes bounded/sub-Gaussian distributions for…

Machine Learning · Computer Science 2023-01-25 Yulian Wu , Chaowen Guan , Vaneet Aggarwal , Di Wang

Sample-efficient offline reinforcement learning (RL) with linear function approximation has recently been studied extensively. Much of prior work has yielded the minimax-optimal bound of $\tilde{\mathcal{O}}(\frac{1}{\sqrt{K}})$, with $K$…

Machine Learning · Computer Science 2023-01-30 Thanh Nguyen-Tang , Ming Yin , Sunil Gupta , Svetha Venkatesh , Raman Arora

We consider reinforcement learning in an environment modeled by an episodic, finite, stage-dependent Markov decision process of horizon $H$ with $S$ states, and $A$ actions. The performance of an agent is measured by the regret after…

In linear stochastic bandits, it is commonly assumed that payoffs are with sub-Gaussian noises. In this paper, under a weaker assumption on noises, we study the problem of \underline{lin}ear stochastic {\underline b}andits with h{\underline…

Machine Learning · Computer Science 2018-11-13 Han Shao , Xiaotian Yu , Irwin King , Michael R. Lyu