English
Related papers

Related papers: Reward Biased Maximum Likelihood Estimation for Re…

200 papers

We consider model selection for classic Reinforcement Learning (RL) environments -- Multi Armed Bandits (MABs) and Markov Decision Processes (MDPs) -- under general function approximations. In the model selection framework, we do not know…

Machine Learning · Statistics 2022-07-08 Avishek Ghosh , Sayak Ray Chowdhury

We advocate for a practical Maximum Likelihood Estimation (MLE) approach towards designing loss functions for regression and forecasting, as an alternative to the typical approach of direct empirical risk minimization on a specific target…

Machine Learning · Statistics 2021-10-12 Pranjal Awasthi , Abhimanyu Das , Rajat Sen , Ananda Theertha Suresh

Reinforcement learning from human feedback (RLHF) provides a principled framework for aligning AI systems with human preference data. For various reasons, e.g., personal bias, context ambiguity, lack of training, etc, human annotators may…

Machine Learning · Computer Science 2024-07-10 Alexander Bukharin , Ilgee Hong , Haoming Jiang , Zichong Li , Qingru Zhang , Zixuan Zhang , Tuo Zhao

Reward design remains a significant bottleneck in applying reinforcement learning (RL) to real-world problems. A popular alternative is reward learning, where reward functions are inferred from human feedback rather than manually specified.…

Machine Learning · Computer Science 2026-01-16 Chaitanya Kharyal , Calarina Muslimani , Matthew E. Taylor

Constrained optimization provides a common framework for dealing with conflicting objectives in reinforcement learning (RL). In most of these settings, the objectives (and constraints) are expressed though the expected accumulated reward.…

Machine Learning · Computer Science 2025-12-03 Jane H. Lee , Baturay Saglam , Spyridon Pougkakiotis , Amin Karbasi , Dionysis Kalogerias

While originally developed for continuous control problems, Proximal Policy Optimization (PPO) has emerged as the work-horse of a variety of reinforcement learning (RL) applications, including the fine-tuning of generative models.…

We revisit the classic regret-minimization problem in the stochastic multi-armed bandit setting when the arm-distributions are allowed to be heavy-tailed. Regret minimization has been well studied in simpler settings of either bounded…

Machine Learning · Computer Science 2021-02-09 Shubhada Agrawal , Sandeep Juneja , Wouter M. Koolen

Upper Confidence Bound (UCB) algorithms are a widely-used class of sequential algorithms for the $K$-armed bandit problem. Despite extensive research over the past decades aimed at understanding their asymptotic and (near) minimax…

Statistics Theory · Mathematics 2024-12-10 Qiyang Han , Koulik Khamaru , Cun-Hui Zhang

In constrained Markov decision processes (CMDPs) with adversarial rewards and constraints, a well-known impossibility result prevents any algorithm from attaining both sublinear regret and sublinear constraint violation, when competing…

Machine Learning · Computer Science 2024-09-27 Francesco Emanuele Stradi , Anna Lunghi , Matteo Castiglioni , Alberto Marchesi , Nicola Gatti

Preference-based Reinforcement Learning (PbRL) replaces reward values in traditional reinforcement learning by preferences to better elicit human opinion on the target objective, especially when numerical reward values are hard to design or…

Machine Learning · Computer Science 2020-10-27 Yichong Xu , Ruosong Wang , Lin F. Yang , Aarti Singh , Artur Dubrawski

We study model-based reinforcement learning (RL) for episodic Markov decision processes (MDP) whose transition probability is parametrized by an unknown transition core with features of state and action. Despite much recent progress in…

Machine Learning · Statistics 2024-11-19 Taehyun Hwang , Min-hwan Oh

We consider an extension to the restless multi-armed bandit (RMAB) problem with unknown arm dynamics, where an unknown exogenous global Markov process governs the rewards distribution of each arm. Under each global state, the rewards…

Machine Learning · Computer Science 2023-01-04 Tomer Gafni , Michal Yemini , Kobi Cohen

We study reinforcement learning (RL) problems in which agents observe the reward or transition realizations at their current state before deciding which action to take. Such observations are available in many applications, including…

Machine Learning · Computer Science 2024-10-22 Nadav Merlis

We study reward maximisation in a wide class of structured stochastic multi-armed bandit problems, where the mean rewards of arms satisfy some given structural constraints, e.g. linear, unimodal, sparse, etc. Our aim is to develop methods…

Machine Learning · Statistics 2020-07-03 Rémy Degenne , Han Shao , Wouter M. Koolen

Traditional reinforcement learning (RL) aims to maximize the expected total reward, while the risk of uncertain outcomes needs to be controlled to ensure reliable performance in a risk-averse setting. In this paper, we consider the problem…

Machine Learning · Computer Science 2023-01-18 Xian Yu , Siqian Shen

We present a new algorithm based on posterior sampling for learning in constrained Markov decision processes (CMDP) in the infinite-horizon undiscounted setting. The algorithm achieves near-optimal regret bounds while being advantageous…

Machine Learning · Computer Science 2023-09-28 Danil Provodin , Pratik Gajane , Mykola Pechenizkiy , Maurits Kaptein

Recent studies have shown that reinforcement learning with KL-regularized objectives can enjoy faster rates of convergence or logarithmic regret, in contrast to the classical $\sqrt{T}$-type regret in the unregularized setting. However, the…

Machine Learning · Computer Science 2026-03-03 Kaixuan Ji , Qingyue Zhao , Heyang Zhao , Qiwei Di , Quanquan Gu

We study an infinite-armed bandit problem where actions' mean rewards are initially sampled from a reservoir distribution. Most prior works in this setting focused on stationary rewards (Berry et al., 1997; Wang et al., 2008; Bonald and…

Machine Learning · Computer Science 2025-02-04 Joe Suk , Jung-hun Kim

Recently, several studies (Zhou et al., 2021a; Zhang et al., 2021b; Kim et al., 2021; Zhou and Gu, 2022) have provided variance-dependent regret bounds for linear contextual bandits, which interpolates the regret for the worst-case regime…

Machine Learning · Computer Science 2023-02-22 Heyang Zhao , Jiafan He , Dongruo Zhou , Tong Zhang , Quanquan Gu

Despite the great interest in the bandit problem, designing efficient algorithms for complex models remains challenging, as there is typically no analytical way to quantify uncertainty. In this paper, we propose Multiplier Bootstrap-based…

Machine Learning · Computer Science 2023-02-06 Runzhe Wan , Haoyu Wei , Branislav Kveton , Rui Song