English
Related papers

Related papers: Similarity as Reward Alignment: Robust and Versati…

200 papers

Reinforcement learning with verifiable rewards has significantly advanced reasoning in large language models (LLMs), but such signals remain coarse, offering only binary correctness feedback. This limitation often results in inefficiencies,…

Machine Learning · Computer Science 2026-04-20 Peixuan Han , Adit Krishnan , Gerald Friedland , Jiaxuan You , Chris Kong

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 preference based reinforcement learning (PbRL), where, unlike traditional reinforcement learning, an agent receives feedback only in terms of a 1 bit (0/1) preference over a trajectory pair instead of absolute…

Machine Learning · Computer Science 2023-02-07 Aldo Pacchiano , Aadirupa Saha , Jonathan Lee

Preference-based reinforcement learning (RL) has shown potential for teaching agents to perform the target tasks without a costly, pre-defined reward function by learning the reward with a supervisor's preference between the two agent…

Machine Learning · Computer Science 2022-03-21 Jongjin Park , Younggyo Seo , Jinwoo Shin , Honglak Lee , Pieter Abbeel , Kimin Lee

The complexity of designing reward functions has been a major obstacle to the wide application of deep reinforcement learning (RL) techniques. Describing an agent's desired behaviors and properties can be difficult, even for experts. A new…

Machine Learning · Computer Science 2024-05-09 Wanqi Xue , Bo An , Shuicheng Yan , Zhongwen Xu

Sampling is ubiquitous in machine learning methodologies. Due to the growth of large datasets and model complexity, we want to learn and adapt the sampling process while training a representation. Towards achieving this grand goal, a…

Machine Learning · Computer Science 2022-12-14 Jason Xiaotian Dou , Alvin Qingkai Pan , Runxue Bao , Haiyi Harry Mao , Lei Luo , Zhi-Hong Mao

Reinforcement Learning from Human Feedback (RLHF) has emerged as a powerful approach for aligning generative models, but its reliance on learned reward models makes it vulnerable to mis-specification and reward hacking. Preference-based…

Machine Learning · Computer Science 2026-04-23 Akhil Agnihotri , Rahul Jain , Deepak Ramachandran , Zheng Wen

Preference-based reinforcement learning (PbRL) has emerged as a promising approach for learning behaviors from human feedback without predefined reward functions. However, current PbRL methods face a critical challenge in effectively…

Artificial Intelligence · Computer Science 2025-06-17 Brahim Driss , Alex Davey , Riad Akrour

Reward models are pivotal for aligning Large Language Models (LLMs) with human preferences. Existing approaches face two key limitations: Discriminative reward models require large-scale annotated data, as they cannot exploit the preference…

Computation and Language · Computer Science 2026-02-03 Yongfu Xue

Preference-based reinforcement learning (PbRL) can enable robots to learn to perform tasks based on an individual's preferences without requiring a hand-crafted reward function. However, existing approaches either assume access to a…

Machine Learning · Computer Science 2024-02-13 Yi Liu , Gaurav Datta , Ellen Novoseller , Daniel S. Brown

Preference-based reinforcement learning (PbRL) provides a powerful paradigm to avoid meticulous reward engineering by learning rewards based on human preferences. However, real-time human feedback is hard to obtain in online tasks. Most…

Machine Learning · Computer Science 2024-12-24 Songjun Tu , Jingbo Sun , Qichao Zhang , Xiangyuan Lan , Dongbin Zhao

When robots learn reward functions using high capacity models that take raw state directly as input, they need to both learn a representation for what matters in the task -- the task ``features" -- as well as how to combine these features…

Robotics · Computer Science 2023-03-20 Andreea Bobu , Yi Liu , Rohin Shah , Daniel S. Brown , Anca D. Dragan

Attention-based sequential recommendation methods have shown promise in accurately capturing users' evolving interests from their past interactions. Recent research has also explored the integration of reinforcement learning (RL) into these…

Machine Learning · Computer Science 2024-04-19 Melissa Mozifian , Tristan Sylvain , Dave Evans , Lili Meng

Safe reinforcement learning (RL) is a standard paradigm for safety-critical decision making. However, real-world safety constraints can be complex, subjective, and even hard to explicitly specify. Existing works on constraint inference rely…

Machine Learning · Computer Science 2026-05-25 Chenglin Li , Grant Ruan , Hua Geng

Post-training has split large language model (LLM) alignment into two largely disconnected tracks. Online reinforcement learning (RL) with verifiable rewards drives emergent reasoning on math and code but depends on a programmatic verifier…

Preference-based reinforcement learning (PbRL) has shown significant promise for personalization in human-robot interaction (HRI) by explicitly integrating human preferences into the robot learning process. However, existing practices often…

Robotics · Computer Science 2025-03-12 Ruiqi Wang , Dezhong Zhao , Dayoon Suh , Ziqin Yuan , Guohua Chen , Byung-Cheol Min

Reward functions are difficult to design and often hard to align with human intent. Preference-based Reinforcement Learning (RL) algorithms address these problems by learning reward functions from human feedback. However, the majority of…

Machine Learning · Computer Science 2023-11-28 Joey Hejna , Dorsa Sadigh

Direct alignment algorithms (DAAs), such as direct preference optimization (DPO), have become popular alternatives for Reinforcement Learning from Human Feedback (RLHF) due to their simplicity, efficiency, and stability. However, the…

Machine Learning · Computer Science 2024-10-15 Jongwoo Ko , Saket Dingliwal , Bhavana Ganesh , Sailik Sengupta , Sravan Bodapati , Aram Galstyan

Offline reinforcement learning (RL) defines a sample-efficient learning paradigm, where a policy is learned from static and previously collected datasets without additional interaction with the environment. The major obstacle to offline RL…

Machine Learning · Computer Science 2022-11-16 Yunfan Zhou , Xijun Li , Qingyu Qu

In preference-based reinforcement learning (PbRL), a reward function is learned from a type of human feedback called preference. To expedite preference collection, recent works have leveraged \emph{offline preferences}, which are…

Machine Learning · Computer Science 2024-03-18 Guoxi Zhang , Han Bao , Hisashi Kashima