English
Related papers

Related papers: HALO: Human Preference Aligned Offline Reward Lear…

200 papers

Robots that can effectively understand human intentions from actions are crucial for successful human-robot collaboration. In this work, we address the challenge of a robot navigating towards an unknown goal while also accounting for a…

Robotics · Computer Science 2023-03-17 Oriana Peltzer , Dylan M. Asmar , Mac Schwager , Mykel J. Kochenderfer

To advance the field of autonomous robotics, particularly in object search tasks within unexplored environments, we introduce a novel framework centered around the Probable Object Location (POLo) score. Utilizing a 3D object probability…

Robotics · Computer Science 2023-11-15 Jiaming Wang , Harold Soh

Multi-turn human-AI collaboration is fundamental to deploying interactive services such as adaptive tutoring, conversational recommendation, and professional consultation. However, optimizing these interactions via reinforcement learning is…

Machine Learning · Computer Science 2026-03-26 Haoyu Wang , Yuxin Chen , Liang Luo , Buyun Zhang , Ellie Dingqiao Wen , Pan Li

Kahneman & Tversky's $\textit{prospect theory}$ tells us that humans perceive random variables in a biased but well-defined manner (1992); for example, humans are famously loss-averse. We show that objectives for aligning LLMs with human…

Machine Learning · Computer Science 2024-11-20 Kawin Ethayarajh , Winnie Xu , Niklas Muennighoff , Dan Jurafsky , Douwe Kiela

Reinforcement learning from human feedback (RLHF) has emerged as a key technique for aligning the output of large language models (LLMs) with human preferences. To learn the reward function, most existing RLHF algorithms use the…

Machine Learning · Statistics 2026-02-11 Kai Ye , Hongyi Zhou , Jin Zhu , Francesco Quinzan , Chengchun Shi

Human alignment in large language models (LLMs) is an active area of research. A recent groundbreaking work, direct preference optimization (DPO), has greatly simplified the process from past work in reinforcement learning from human…

Computation and Language · Computer Science 2025-03-10 Changyu Chen , Zichen Liu , Chao Du , Tianyu Pang , Qian Liu , Arunesh Sinha , Pradeep Varakantham , Min Lin

In reinforcement learning (RL), sparse rewards are a natural way to specify the task to be learned. However, most RL algorithms struggle to learn in this setting since the learning signal is mostly zeros. In contrast, humans are good at…

We present an approach to robot learning from egocentric human videos by modeling human preferences in a reward function and optimizing robot behavior to maximize this reward. Prior work on reward learning from human videos attempts to…

Robotics · Computer Science 2026-02-13 Mrinal Verghese , Christopher G. Atkeson

The rapid development of large language model (LLM) alignment algorithms has resulted in a complex and fragmented landscape, with limited clarity on the effectiveness of different methods and their inter-connections. This paper introduces…

Imitation learning holds tremendous promise in learning policies efficiently for complex decision making problems. Current state-of-the-art algorithms often use inverse reinforcement learning (IRL), where given a set of expert…

Robotics · Computer Science 2023-02-22 Siddhant Haldar , Vaibhav Mathur , Denis Yarats , Lerrel Pinto

The current reward learning from human preferences could be used to resolve complex reinforcement learning (RL) tasks without access to a reward function by defining a single fixed preference between pairs of trajectory segments. However,…

Artificial Intelligence · Computer Science 2020-12-29 Zehong Cao , KaiChiu Wong , Chin-Teng Lin

Offline reinforcement learning methods hold the promise of learning policies from pre-collected datasets without the need to query the environment for new transitions. This setting is particularly well-suited for continuous control robotic…

Machine Learning · Computer Science 2022-03-18 Xi Chen , Ali Ghadirzadeh , Tianhe Yu , Yuan Gao , Jianhao Wang , Wenzhe Li , Bin Liang , Chelsea Finn , Chongjie Zhang

Robots operating in human-centered environments should have the ability to understand how objects function: what can be done with each object, where this interaction may occur, and how the object is used to achieve a goal. To this end, we…

Hyperparameter optimization (HPO) is important to leverage the full potential of machine learning (ML). In practice, users are often interested in multi-objective (MO) problems, i.e., optimizing potentially conflicting objectives, like…

Machine Learning · Computer Science 2024-01-12 Joseph Giovanelli , Alexander Tornede , Tanja Tornede , Marius Lindauer

Hierarchical Imitation Learning (HIL) has been proposed to recover highly-complex behaviors in long-horizon tasks from expert demonstrations by modeling the task hierarchy with the option framework. Existing methods either overlook the…

Machine Learning · Computer Science 2023-05-29 Jiayu Chen , Tian Lan , Vaneet Aggarwal

While classical approaches to autonomous robot navigation currently enable operation in certain environments, they break down in tightly constrained spaces, e.g., where the robot needs to engage in agile maneuvers to squeeze between…

Robotics · Computer Science 2021-01-21 Xuesu Xiao , Bo Liu , Garrett Warnell , Peter Stone

Reward inference (learning a reward model from human preferences) is a critical intermediate step in the Reinforcement Learning from Human Feedback (RLHF) pipeline for fine-tuning Large Language Models (LLMs). In practice, RLHF faces…

Machine Learning · Computer Science 2025-03-04 Qining Zhang , Lei Ying

Distance-based reward mechanisms in deep reinforcement learning (DRL) navigation systems suffer from critical safety limitations in dynamic environments, frequently resulting in collisions when visibility is restricted. We propose DRL-NSUO,…

Robotics · Computer Science 2025-03-04 Mingao Tan , Shanze Wang , Biao Huang , Zhibo Yang , Rongfei Chen , Xiaoyu Shen , Wei Zhang

Learning from human feedback has gained traction in fields like robotics and natural language processing in recent years. While prior works mostly rely on human feedback in the form of comparisons, language is a preferable modality that…

Robotics · Computer Science 2024-10-10 Zhaojing Yang , Miru Jun , Jeremy Tien , Stuart J. Russell , Anca Dragan , Erdem Bıyık

To fluently collaborate with people, robots need the ability to recognize human activities accurately. Although modern robots are equipped with various sensors, robust human activity recognition (HAR) still remains a challenging task for…

Robotics · Computer Science 2020-08-17 Md Mofijul Islam , Tariq Iqbal