English
Related papers

Related papers: Distribution-Aware Reward Estimation for Test-Time…

200 papers

Reinforcement learning with verifiable rewards (RLVR) enhances the reasoning of large language models (LLMs), but standard RLVR often depends on human-annotated answers or carefully curated reward specifications. In machine-checkable…

Artificial Intelligence · Computer Science 2026-04-29 Xinjie Chen , Biao Fu , Jing Wu , Guoxin Chen , Xinggao Liu , Dayiheng Liu , Minpeng Liao

Distributional reinforcement learning (DRL) enhances the understanding of the effects of the randomness in the environment by letting agents learn the distribution of a random return, rather than its expected value as in standard RL. At the…

Optimization and Control · Mathematics 2023-03-27 Zifan Wang , Yulong Gao , Siyi Wang , Michael M. Zavlanos , Alessandro Abate , Karl H. Johansson

Large language models (LLMs) are inherently vulnerable to unintended privacy breaches. Consequently, systematic red-teaming research is essential for developing robust defense mechanisms. However, current data extraction methods suffer from…

Machine Learning · Computer Science 2025-05-13 Zhiqiang Wang , Ruoxi Cheng

Distribution system state estimation (DSSE) is paramount for effective state monitoring and control. However, stochastic outputs of renewables and asynchronous streaming of multi-rate measurements in practical systems largely degrade the…

Systems and Control · Electrical Eng. & Systems 2023-10-23 Ying Zhang , Junbo Zhao , Di Shi , Sungjoo Chung

Reinforcement learning algorithms are typically designed for discrete-time dynamics, even though the underlying real-world control systems are often continuous in time. In this paper, we study the problem of continuous-time reinforcement…

Machine Learning · Computer Science 2026-03-03 Klemens Iten , Lenart Treven , Bhavya Sukhija , Florian Dörfler , Andreas Krause

Recent advances such as self-consistency and test-time reinforcement learning (TTRL) improve the reliability of large language models (LLMs) without additional supervision, yet their underlying mechanisms and statistical guarantees remain…

Machine Learning · Statistics 2025-10-24 Paula Cordero-Encinar , Andrew B. Duncan

Test-time reinforcement learning (TTRL) reports substantial accuracy gains on mathematical reasoning benchmarks using majority vote as a pseudo-label signal. We argue these gains are systematically misinterpreted: most reflect sharpening of…

Machine Learning · Computer Science 2026-05-28 Hongxiang Lin , Zhirui Kuai , Erpeng Xue , Lei Wang

Credit assignmen, disentangling each agent's contribution to a shared reward, is a critical challenge in cooperative multi-agent reinforcement learning (MARL). To be effective, credit assignment methods must preserve the environment's…

Multiagent Systems · Computer Science 2025-10-30 Aditya Kapoor , Kale-ab Tessera , Mayank Baranwal , Harshad Khadilkar , Jan Peters , Stefano Albrecht , Mingfei Sun

In Reinforcement Learning (RL), designing precise reward functions remains to be a challenge, particularly when aligning with human intent. Preference-based RL (PbRL) was introduced to address this problem by learning reward models from…

Machine Learning · Computer Science 2024-08-09 Heewoong Choi , Sangwon Jung , Hongjoon Ahn , Taesup Moon

We consider the problem of reward learning for temporally extended tasks. For reward learning, inverse reinforcement learning (IRL) is a widely used paradigm. Given a Markov decision process (MDP) and a set of demonstrations for a task, IRL…

Robotics · Computer Science 2021-07-14 Farzan Memarian , Zhe Xu , Bo Wu , Min Wen , Ufuk Topcu

Deep Reinforcement Learning (DRL) is a promising approach for teaching robots new behaviour. However, one of its main limitations is the need for carefully hand-coded reward signals by an expert. We argue that it is crucial to automate the…

Robotics · Computer Science 2021-08-09 Abdalkarim Mohtasib , Gerhard Neumann , Heriberto Cuayahuitl

Despite their empirical success, most existing listwiselearning-to-rank (LTR) models are not built to be robust to errors in labeling or annotation, distributional data shift, or adversarial data perturbations. To fill this gap, we…

Machine Learning · Computer Science 2021-09-28 Shahabeddin Sotudian , Ruidi Chen , Ioannis Paschalidis

Model-based reinforcement learning (MBRL) has gained much attention for its ability to learn complex behaviors in a sample-efficient way: planning actions by generating imaginary trajectories with predicted rewards. Despite its success, we…

Machine Learning · Computer Science 2024-02-20 Vint Lee , Pieter Abbeel , Youngwoon Lee

Large Language Models (LLMs) demonstrate transformative potential, yet their reasoning remains inconsistent and unreliable. Reinforcement learning (RL)-based fine-tuning is a key mechanism for improvement, but its effectiveness is…

Machine Learning · Computer Science 2026-02-11 Pei-Chi Pan , Yingbin Liang , Sen Lin

Recovering reward function from expert demonstrations is a fundamental problem in reinforcement learning. The recovered reward function captures the motivation of the expert. Agents can imitate experts by following these reward functions in…

Machine Learning · Computer Science 2024-06-27 Fan-Ming Luo , Xingchen Cao , Rong-Jun Qin , Yang Yu

Reward models (RMs) are essential for aligning large language models (LLM) with human expectations. However, existing RMs struggle to capture the stochastic and uncertain nature of human preferences and fail to assess the reliability of…

Machine Learning · Computer Science 2025-02-13 Xingzhou Lou , Dong Yan , Wei Shen , Yuzi Yan , Jian Xie , Junge Zhang

Alignment is vital for safely deploying large language models (LLMs). Existing techniques are either reward-based (training a reward model on preference pairs and optimizing with reinforcement learning) or reward-free (directly fine-tuning…

Computation and Language · Computer Science 2026-03-03 Ruoxi Cheng , Haoxuan Ma , Weixin Wang , Ranjie Duan , Jiexi Liu , Xiaoshuang Jia , Simeng Qin , Xiaochun Cao , Yang Liu , Xiaojun Jia

In this paper, we investigate the problem of offline Preference-based Reinforcement Learning (PbRL) with human feedback where feedback is available in the form of preference between trajectory pairs rather than explicit rewards. Our…

Machine Learning · Computer Science 2023-10-03 Wenhao Zhan , Masatoshi Uehara , Nathan Kallus , Jason D. Lee , Wen Sun

Reinforcement Learning with Verifiable Rewards (RLVR), particularly with algorithms like Group Relative Policy Optimization (GRPO), has proven highly effective in enhancing the reasoning capabilities of large language models. However, a…

Computation and Language · Computer Science 2026-03-03 Shangyu Xing , Siyuan Wang , Chenyuan Yang , Xinyu Dai , Xiang Ren

Offline reinforcement learning (RL) provides a powerful framework for training robotic agents using pre-collected, suboptimal datasets, eliminating the need for costly, time-consuming, and potentially hazardous online interactions. This is…

Machine Learning · Computer Science 2025-08-01 Tung M. Luu , Donghoon Lee , Younghwan Lee , Chang D. Yoo