English
Related papers

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

200 papers

Reward models are crucial for aligning large language models (LLMs) with human values and intentions. Existing approaches follow either Generative (GRMs) or Discriminative (DRMs) paradigms, yet both suffer from limitations: GRMs typically…

Computation and Language · Computer Science 2026-03-03 Longze Chen , Lu Wang , Renke Shan , Ze Gong , Run Luo , Jiaming Li , Jing Luo , Qiyao Wang , Min Yang

Resource allocation plays a critical role in minimizing cycle time and improving the efficiency of business processes. Recently, Deep Reinforcement Learning (DRL) has emerged as a powerful technique to optimize resource allocation policies…

Machine Learning · Computer Science 2025-09-03 Jeroen Middelhuis , Zaharah Bukhsh , Ivo Adan , Remco Dijkman

Distributional reinforcement learning (DRL) has achieved empirical success in various domains. One core task in DRL is distributional policy evaluation, which involves estimating the return distribution $\eta^\pi$ for a given policy $\pi$.…

Machine Learning · Statistics 2025-01-17 Yang Peng , Liangyu Zhang , Zhihua Zhang

Multi-agent systems have evolved into practical LLM-driven collaborators for many applications, gaining robustness from diversity and cross-checking. However, multi-agent RL (MARL) training is resource-intensive and unstable: co-adapting…

Offline-to-online reinforcement learning (O2O RL) faces a central challenge between retaining offline conservatism and adapting to online feedback under distribution shift. This challenge arises because data behavior evolves during…

Machine Learning · Computer Science 2026-05-19 Lipeng Zu , Yu Qian , Shayok Chakraborty , Xiaonan Zhang

Reinforcement learning with verifiable rewards (RLVR) has emerged as an effective post-training paradigm for improving the reasoning capabilities of large language models. However, existing group-based RLVR methods often suffer from severe…

Machine Learning · Computer Science 2026-05-26 Haechan Kim , Soohyun Ryu , Gyouk Chu , Doohyuk Jang , Eunho Yang

A common explanation for the failure of deep networks to generalize out-of-distribution is that they fail to recover the "correct" features. We challenge this notion with a simple experiment which suggests that ERM already learns sufficient…

Machine Learning · Computer Science 2022-10-31 Elan Rosenfeld , Pradeep Ravikumar , Andrej Risteski

Test-time scaling (TTS) for large language models (LLMs) has thus far fallen into two largely separate paradigms: (1) reinforcement learning (RL) methods that optimize sparse outcome-based rewards, yet suffer from instability and low sample…

Machine Learning · Computer Science 2026-02-10 Can Jin , Yang Zhou , Qixin Zhang , Hongwu Peng , Di Zhang , Zihan Dong , Marco Pavone , Ligong Han , Zhang-Wei Hong , Tong Che , Dimitris N. Metaxas

In this work, we present Transitive Reinforcement Learning (TRL), a new value learning algorithm based on a divide-and-conquer paradigm. TRL is designed for offline goal-conditioned reinforcement learning (GCRL) problems, where the aim is…

Machine Learning · Computer Science 2026-02-24 Seohong Park , Aditya Oberai , Pranav Atreya , Sergey Levine

When decisions are made at high frequency, traditional reinforcement learning (RL) methods struggle to accurately estimate action values. In turn, their performance is inconsistent and often poor. Whether the performance of distributional…

Machine Learning · Computer Science 2024-10-16 Harley Wiltzer , Marc G. Bellemare , David Meger , Patrick Shafto , Yash Jhaveri

The availability of large pre-trained models is changing the landscape of Machine Learning research and practice, moving from a training-from-scratch to a fine-tuning paradigm. While in some applications the goal is to "nudge" the…

Machine Learning · Computer Science 2022-11-15 Tomasz Korbak , Hady Elsahar , Germán Kruszewski , Marc Dymetman

Reinforcement learning (RL) is pivotal for enhancing the reasoning capabilities of diffusion large language models (dLLMs). However, existing dLLM policy optimization methods suffer from two critical reliability bottlenecks: (1) reward…

Computation and Language · Computer Science 2026-05-14 Leyi Pan , Shuchang Tao , Yunpeng Zhai , Zheyu Fu , Liancheng Fang , Minghua He , Lingzhe Zhang , Zhaoyang Liu , Bolin Ding , Aiwei Liu , Lijie Wen

In Reinforcement Learning (RL), it is commonly assumed that an immediate reward signal is generated for each action taken by the agent, helping the agent maximize cumulative rewards to obtain the optimal policy. However, in many real-world…

Machine Learning · Computer Science 2024-10-29 Yuting Tang , Xin-Qiang Cai , Yao-Xiang Ding , Qiyu Wu , Guoqing Liu , Masashi Sugiyama

External test-time reasoning enhances large language models (LLMs) by decoupling generation and selection. At inference time, the model generates multiple reasoning paths, and an auxiliary process reward model (PRM) is used to score and…

Machine Learning · Computer Science 2025-05-26 Zeen Song , Wenwen Qiang , Siyu Zhao , Changwen Zheng , Gang Hua

Recent analyses question whether reinforcement learning (RL) is responsible for strong reasoning in large language models (LLMs). At the same time, distillation and inference-time sampling, including power sampling, have emerged as…

Machine Learning · Computer Science 2026-05-07 Akiyoshi Tomihari , Issei Sato

Seeking to improve model generalization, we consider a new approach based on distributionally robust learning (DRL) that applies stochastic gradient descent to the outer minimization problem. Our algorithm efficiently estimates the gradient…

Machine Learning · Statistics 2020-12-24 Soumyadip Ghosh , Mark Squillante

This paper considers multi-agent reinforcement learning (MARL) tasks where agents receive a shared global reward at the end of an episode. The delayed nature of this reward affects the ability of the agents to assess the quality of their…

Multiagent Systems · Computer Science 2022-01-13 Baicen Xiao , Bhaskar Ramasubramanian , Radha Poovendran

Frontier models have demonstrated exceptional capabilities following the integration of task-reward-based reinforcement learning (RL) into their training pipelines, enabling systems to evolve from pure reasoning models into sophisticated…

Machine Learning · Computer Science 2026-04-20 Sarthak Mittal , Leo Gagnon , Guillaume Lajoie

Inverse reinforcement learning (IRL) aims to explicitly infer an underlying reward function based on collected expert demonstrations. Considering that obtaining expert demonstrations can be costly, the focus of current IRL techniques is on…

Machine Learning · Computer Science 2023-10-16 Lu Li , Yuxin Pan , Ruobing Chen , Jie Liu , Zilin Wang , Yu Liu , Zhiheng Li

Existing methods for extracting reward signals in Reinforcement Learning typically rely on labeled data and dedicated training splits, a setup that contrasts with how humans learn directly from their environment. In this work, we propose…

Computer Vision and Pattern Recognition · Computer Science 2025-12-05 Akshit Singh , Shyam Marjit , Wei Lin , Paul Gavrikov , Serena Yeung-Levy , Hilde Kuehne , Rogerio Feris , Sivan Doveh , James Glass , M. Jehanzeb Mirza