English
Related papers

Related papers: Predictive Preference Learning from Human Interven…

200 papers

We develop a simple framework to learn bio-inspired foraging policies using human data. We conduct an experiment where humans are virtually immersed in an open field foraging environment and are trained to collect the highest amount of…

Interactive NLP is a promising paradigm to close the gap between automatic NLP systems and the human upper bound. Preference-based interactive learning has been successfully applied, but the existing methods require several thousand…

Computation and Language · Computer Science 2019-06-10 Yang Gao , Christian M. Meyer , Iryna Gurevych

Smart assistants increasingly act proactively, yet mistimed or intrusive behavior often causes users to lose trust and disable these features. Learning user preferences for proactive assistance is difficult because real-world studies are…

Human-Computer Interaction · Computer Science 2026-02-05 Ziyi Xuan , Yiwen Wu , Zhaoyang Yan , Vinod Namboodiri , Yu Yang

The prevalent deployment of learning from human preferences through reinforcement learning (RLHF) relies on two important approximations: the first assumes that pairwise preferences can be substituted with pointwise rewards. The second…

Artificial Intelligence · Computer Science 2023-11-23 Mohammad Gheshlaghi Azar , Mark Rowland , Bilal Piot , Daniel Guo , Daniele Calandriello , Michal Valko , Rémi Munos

Preference-based reinforcement learning is an effective way to handle tasks where rewards are hard to specify but can be exceedingly inefficient as preference learning is often tabula rasa. We demonstrate that Large Language Models (LLMs)…

Artificial Intelligence · Computer Science 2025-04-04 Chao Yu , Qixin Tan , Hong Lu , Jiaxuan Gao , Xinting Yang , Yu Wang , Yi Wu , Eugene Vinitsky

Modern AI agents are powerful but often fail to align with the idiosyncratic, evolving preferences of individual users. Prior approaches typically rely on static datasets, either training implicit preference models on interaction history or…

Preference-based feedback is important for many applications in machine learning where evaluation of a reward function is not feasible. Notable recent examples arise in preference alignment for large language models, including in…

Accommodating human preferences is essential for creating AI agents that deliver personalized and effective interactions. Recent work has shown the potential for LLMs to infer preferences from user interactions, but they often produce broad…

Artificial Intelligence · Computer Science 2024-10-10 Stephane Aroca-Ouellette , Natalie Mackraz , Barry-John Theobald , Katherine Metcalf

Learning from demonstrations is a common way for users to teach robots, but it is prone to spurious feature correlations. Recent work constructs state abstractions, i.e. visual representations containing task-relevant features, from…

Reinforcement learning from human feedback (RLHF) has emerged as the primary method for aligning large language models (LLMs) with human preferences. While it enables LLMs to achieve human-level alignment, it often incurs significant…

Computation and Language · Computer Science 2025-03-21 Shivank Garg , Ayush Singh , Shweta Singh , Paras Chopra

Robot motion planning often requires finding trajectories that balance different user intents, or preferences. One of these preferences is usually arrival at the goal, while another might be obstacle avoidance. Here, we formalize these, and…

Robotics · Computer Science 2018-12-03 Aleksandra Faust , Hao-Tien Lewis Chiang , Lydia Tapia

Preference learning has long been studied in Human-Robot Interaction (HRI) in order to adapt robot behavior to specific user needs and desires. Typically, human preferences are modeled as a scalar function; however, such a formulation…

Robotics · Computer Science 2024-04-01 Austin Narcomey , Nathan Tsoi , Ruta Desai , Marynel Vázquez

When operating in service of people, robots need to optimize rewards aligned with end-user preferences. Since robots will rely on raw perceptual inputs like RGB images, their rewards will inevitably use visual representations. Recently…

Robotics · Computer Science 2024-01-17 Ran Tian , Chenfeng Xu , Masayoshi Tomizuka , Jitendra Malik , Andrea Bajcsy

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

A goal of Interactive Machine Learning (IML) is to enable people without specialized training to teach agents how to perform tasks. Many of the existing machine learning algorithms that learn from human instructions are evaluated using…

Human-Computer Interaction · Computer Science 2018-04-17 Samantha Krening

The inputs and preferences of human users are important considerations in situations where these users interact with autonomous cyber or cyber-physical systems. In these scenarios, one is often interested in aligning behaviors of the system…

Machine Learning · Computer Science 2021-04-02 Bhaskar Ramasubramanian , Luyao Niu , Andrew Clark , Radha Poovendran

Multi-objective reinforcement learning (MORL) is a structured approach for optimizing tasks with multiple objectives. However, it often relies on pre-defined reward functions, which can be hard to design for balancing conflicting goals and…

Machine Learning · Computer Science 2025-07-21 Ni Mu , Yao Luan , Qing-Shan Jia

Preference-based reinforcement learning (RL) provides a framework to train AI agents using human feedback through preferences over pairs of behaviors, enabling agents to learn desired behaviors when it is difficult to specify a numerical…

Human-Computer Interaction · Computer Science 2025-03-21 David Chhan , Ellen Novoseller , Vernon J. Lawhern

The recent surge of versatile large language models (LLMs) largely depends on aligning increasingly capable foundation models with human intentions by preference learning, enhancing LLMs with excellent applicability and effectiveness in a…

Computation and Language · Computer Science 2024-06-19 Ruili Jiang , Kehai Chen , Xuefeng Bai , Zhixuan He , Juntao Li , Muyun Yang , Tiejun Zhao , Liqiang Nie , Min Zhang

Visuomotor robot policies, increasingly pre-trained on large-scale datasets, promise significant advancements across robotics domains. However, aligning these policies with end-user preferences remains a challenge, particularly when the…

Robotics · Computer Science 2024-12-09 Ran Tian , Yilin Wu , Chenfeng Xu , Masayoshi Tomizuka , Jitendra Malik , Andrea Bajcsy