Related papers: Active Reward Learning from Online Preferences

Machine learning models are being increasingly deployed to take, or assist in taking, complicated and high-impact decisions, from quasi-autonomous vehicles to clinical decision support systems. This poses challenges, particularly when…

Designing reward functions for continuous-control robotics often leads to subtle misalignments or reward hacking, especially in complex tasks. Preference-based RL mitigates some of these pitfalls by learning rewards from comparative…

We propose a method to capture the handling abilities of fast jet pilots in a software model via reinforcement learning (RL) from human preference feedback. We use pairwise preferences over simulated flight trajectories to learn an…

To effectively assist human workers in assembly tasks a robot must proactively offer support by inferring their preferences in sequencing the task actions. Previous work has focused on learning the dominant preferences of human workers for…

For effective real-world deployment, robots should adapt to human preferences, such as balancing distance, time, and safety in delivery routing. Active preference learning (APL) learns human reward functions by presenting trajectories for…

Different machine learning techniques have been proposed and used for modeling individual and group user needs, interests and preferences. In the traditional predictive modeling instances are described by observable variables, called…

Evaluating learned robot control policies to determine their physical task-level capabilities costs experimenter time and effort. The growing number of policies and tasks exacerbates this issue. It is impractical to test every policy on…

It is intractable for assistive robots to have all functionalities pre-programmed prior to deployment. Rather, it is more realistic for robots to perform supplemental, on-site learning about user's needs and preferences, and particularities…

Assistive agents should be able to perform under-specified long-horizon tasks while respecting user preferences. We introduce Actively Discovering and Adapting to Preferences for any Task (ADAPT) -- a benchmark designed to evaluate agents'…

Robot-assisted navigation is a perfect example of a class of applications requiring flexible control approaches. When the human is reliable, the robot should concede space to their initiative. When the human makes inappropriate choices the…

Preference-based reinforcement learning (PbRL) can help avoid sophisticated reward designs and align better with human intentions, showing great promise in various real-world applications. However, obtaining human feedback for preferences…

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…

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,…

Most methods for decision-theoretic online learning are based on the Hedge algorithm, which takes a parameter called the learning rate. In most previous analyses the learning rate was carefully tuned to obtain optimal worst-case…

Designers of AI agents often iterate on the reward function in a trial-and-error process until they get the desired behavior, but this only guarantees good behavior in the training environment. We propose structuring this process as a…

Humanoid robotics has strong potential to transform daily service and caregiving applications. Although recent advances in general motion tracking within physics engines (GMT) have enabled virtual characters and humanoid robots to reproduce…

As robots and other intelligent agents move from simple environments and problems to more complex, unstructured settings, manually programming their behavior has become increasingly challenging and expensive. Often, it is easier for a…

The correct specification of reward models is a well-known challenge in reinforcement learning. Hand-crafted reward functions often lead to inefficient or suboptimal policies and may not be aligned with user values. Reinforcement learning…

Reinforcement Learning from Human Feedback (RLHF) typically relies on static reward models to align Large Language Models with human preferences. However, human values are inherently diverse and heterogeneous, and a single reward model…

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…