Related papers: The Impact of Reference-Command Preview on Human-i…
Reaction time studies with computers investigate how and how quickly participants respond to changing sensory input. They promise simple and precise measurement of time and inputs and offer interesting insights into human behavior. However,…
Due to the potentially large number of units involved, the interaction with a multi-robot system is likely to exceed the limits of the span of apprehension of any individual human operator. In previous work, we studied how this issue can be…
In this paper, we propose a reinforcement learning-based algorithm for trajectory optimization for constrained dynamical systems. This problem is motivated by the fact that for most robotic systems, the dynamics may not always be known.…
Neurofeedback has proved to be useful in many instances. This technique is often used to address both medical issues and performance improvement. Despite the wide range of applications, no consensus has been reached about the optimal…
Preference-based reinforcement learning (PbRL) aligns a robot behavior with human preferences via a reward function learned from binary feedback over agent behaviors. We show that dynamics-aware reward functions improve the sample…
Truly proactive AI systems must anticipate what we will do next. This foresight demands far richer information than the sparse signals we type into our prompts -- it demands reasoning over the entire context of what we see and do. We…
Reinforcement Learning (RL) has seen many recent successes for quadruped robot control. The imitation of reference motions provides a simple and powerful prior for guiding solutions towards desired solutions without the need for meticulous…
Backdoor attacks inject poisoning samples during training, with the goal of forcing a machine learning model to output an attacker-chosen class when presented a specific trigger at test time. Although backdoor attacks have been demonstrated…
Computer-assisted multimodal training is an effective way of learning complex motor skills in various applications. In particular disciplines (eg. healthcare) incompetency in performing dexterous hands-on examinations (clinical palpation)…
Early identification of at risk students in higher education depends on predictive models that maintain accuracy across successive cohorts -- a requirement that single-cohort modeling approaches fail to meet. This study evaluates Bayesian…
Learning about many things can provide numerous benefits to a reinforcement learning system. For example, learning many auxiliary value functions, in addition to optimizing the environmental reward, appears to improve both exploration and…
Robots are expected to replace menial tasks such as housework. Some of these tasks include nonprehensile manipulation performed without grasping objects. Nonprehensile manipulation is very difficult because it requires considering the…
Inspired by human learning, researchers have proposed ordering examples during training based on their difficulty. Both curriculum learning, exposing a network to easier examples early in training, and anti-curriculum learning, showing the…
Language models (LMs) trained on vast quantities of unlabelled data have greatly advanced the field of natural language processing (NLP). In this study, we re-visit the widely accepted notion in NLP that continued pre-training LMs on…
Learning a general humanoid whole-body controller is challenging because practical reference motions can exhibit noise and inconsistencies after being transferred to the robot domain, and local defects may be amplified by closed-loop…
While advancements in the reasoning abilities of LLMs have significantly enhanced their performance in solving mathematical problems, coding tasks, and general puzzles, their effectiveness in accurately adhering to instructions remains…
Preference learning is a widely adopted post-training technique that aligns large language models (LLMs) to human preferences and improves specific downstream task capabilities. In this work we systematically investigate how specific…
For group-living animals, reaching consensus to stay cohesive is crucial for their fitness, particularly when collective motion starts and stops. Understanding the decision-making at individual and collective levels upon sudden disturbances…
We develop a learning-based control algorithm for unknown dynamical systems under very severe data limitations. Specifically, the algorithm has access to streaming and noisy data only from a single and ongoing trial. It accomplishes such…
Free-standing social conversations constitute a yet underexplored setting for human behavior forecasting. While the task of predicting pedestrian trajectories has received much recent attention, an intrinsic difference between these…