English
Related papers

Related papers: Random Reward Phase-Type Distributions with Applic…

200 papers

A non linear regression approach which consists of a specific regression model incorporating a latent process, allowing various polynomial regression models to be activated preferentially and smoothly, is introduced in this paper. The model…

Statistics Theory · Mathematics 2013-12-30 Faicel Chamroukhi , Allou Samé , Gérard Govaert , Patrice Aknin

Tool use enables large language models to solve complex tasks through sequences of API calls, yet existing reinforcement learning approaches fail to scale to multi-step composition settings. Outcome-based rewards provide only sparse…

Machine Learning · Computer Science 2026-05-19 Anay Kulkarni , ChiaEn Lu , Dheeraj Mekala , Jayanth Srinivasa , Gaowen Liu , Jingbo Shang

Reward models (RMs) are essential in reinforcement learning from human feedback (RLHF) to align large language models (LLMs) with human values. However, RM training data is commonly recognized as low-quality, containing inductive biases…

Machine Learning · Computer Science 2026-05-20 Zhuo Li , Pengyu Cheng , Zhechao Yu , Feifei Tong , Anningzhe Gao , Tsung-Hui Chang , Xiang Wan , Erchao Zhao , Xiaoxi Jiang , Guanjun Jiang

Reinforcement Learning (RL) heavily relies on the careful design of the reward function. However, accurately assigning rewards to each state-action pair in Long-Term Reinforcement Learning (LTRL) tasks remains a significant challenge. As a…

Machine Learning · Computer Science 2025-06-03 Qi Ju , Falin Hei , Zhemei Fang , Yunfeng Luo

This paper introduces the distributionally robust random utility model (DRO-RUM), which allows the preference shock (unobserved heterogeneity) distribution to be misspecified or unknown. We make three contributions using tools from the…

Theoretical Economics · Economics 2023-03-13 David Müller , Emerson Melo , Ruben Schlotter

Reward models in RLHF are trained to score only the final token of a response - a choice that discards rich signal from every intermediate position and produces models whose token-level outputs are noise. We argue this is a missed…

Machine Learning · Computer Science 2026-04-28 Alex Nikulkov

Automatically synthesizing dense rewards from natural language descriptions is a promising paradigm in reinforcement learning (RL), with applications to sparse reward problems, open-ended exploration, and hierarchical skill design. Recent…

Machine Learning · Computer Science 2025-10-27 Qinqing Zheng , Mikael Henaff , Amy Zhang , Aditya Grover , Brandon Amos

Reinforcement learning from human feedback (RLHF) has become a key method for aligning large language models (LLMs) with human preferences through the use of reward models. However, traditional reward models typically generate point…

Machine Learning · Computer Science 2024-09-17 Nicolai Dorka

The statistical modeling of discrete extremes has received less attention than their continuous counterparts in the Extreme Value Theory (EVT) literature. One approach to the transition from continuous to discrete extremes is the modeling…

Methodology · Statistics 2024-06-18 Touqeer Ahmad , Carlo Gaetan , Philippe Naveau

In this paper, a new three-parameter lifetime distribution is introduced and many of its standard properties are discussed. These include shape of the probability density function, hazard rate function and its shape, quantile function,…

Methodology · Statistics 2013-08-21 Min Wang

This paper presents a novel form of policy gradient for model-free reinforcement learning (RL) with improved exploration properties. Current policy-based methods use entropy regularization to encourage undirected exploration of the reward…

Machine Learning · Computer Science 2017-03-17 Ofir Nachum , Mohammad Norouzi , Dale Schuurmans

Reinforcement Learning from Human Feedback (RLHF) typically relies on static reward models to align Large Language Models with human preferences. However, human values are inherently diverse and heterogeneous, and a single reward model…

Machine Learning · Computer Science 2026-05-29 Zhenyu Sun , Zheng Xu , Ermin Wei

The standard feedback model of reinforcement learning requires revealing the reward of every visited state-action pair. However, in practice, it is often the case that such frequent feedback is not available. In this work, we take a first…

Machine Learning · Computer Science 2021-03-08 Yonathan Efroni , Nadav Merlis , Shie Mannor

Conveying complex objectives to reinforcement learning (RL) agents often requires meticulous reward engineering. Preference-based RL methods are able to learn a more flexible reward model based on human preferences by actively incorporating…

Machine Learning · Computer Science 2022-05-26 Xinran Liang , Katherine Shu , Kimin Lee , Pieter Abbeel

We explore the methodology and theory of reward-directed generation via conditional diffusion models. Directed generation aims to generate samples with desired properties as measured by a reward function, which has broad applications in…

Machine Learning · Computer Science 2023-07-17 Hui Yuan , Kaixuan Huang , Chengzhuo Ni , Minshuo Chen , Mengdi Wang

Fine-tuned large language models can exhibit reward-hacking behavior arising from emergent misalignment, which is difficult to detect from final outputs alone. While prior work has studied reward hacking at the level of completed responses,…

Computation and Language · Computer Science 2026-03-05 Patrick Wilhelm , Thorsten Wittkopp , Odej Kao

The class of $\alpha$-stable distributions with a wide range of applications in economics, telecommunications, biology, applied, and theoretical physics. This is due to the fact that it possesses both the skewness and heavy tails. Since…

Statistics Theory · Mathematics 2018-11-13 Mahdi Teimouri

Discrete diffusion models have recently emerged as strong alternatives to autoregressive language models, matching their performance through large-scale training. However, inference-time control remains relatively underexplored. In this…

Machine Learning · Computer Science 2026-04-09 Meihua Dang , Jiaqi Han , Minkai Xu , Kai Xu , Akash Srivastava , Stefano Ermon

A common recipe to improve diffusion models at test-time so that samples score highly against a user-specified reward is to introduce the gradient of the reward into the dynamics of the diffusion itself. This procedure is often ill posed,…

Products between phase-type distributed random variables and any independent, positive and continuous random variable are studied. Their asymptotic properties are established, and an expectation-maximization algorithm for their effective…

Probability · Mathematics 2021-11-25 Hansjoerg Albrecher , Martin Bladt , Mogens Bladt , Jorge Yslas
‹ Prev 1 3 4 5 6 7 10 Next ›