6 accepted papers
Action advising is a knowledge transfer technique for reinforcement learning based on the teacher-student paradigm. An expert teacher provides advice to a student during training in order to improve the student's sample efficiency and policy performance. Such advice is commonly given in the form of…
While Large Language Models (LLMs) have demonstrated impressive accomplishments in both reasoning and planning, their abilities in multi-agent collaborations remains largely unexplored. This study evaluates LLM-based agents in a multi-agent cooperative text game with Theory of Mind (ToM) inference t…
Multi-agent robotic systems are increasingly operating in real-world environments in close proximity to humans, yet are largely controlled by policy models with inscrutable deep neural network representations. We introduce a method for incorporating interpretable concepts from a domain expert into m…
Neural agents trained in reinforcement learning settings can learn to communicate among themselves via discrete tokens, accomplishing as a team what agents would be unable to do alone. However, the current standard of using one-hot vectors as discrete communication tokens prevents agents from acquir…
We describe a flexible robotic skin module that can measure proximity, contact and force, as well as algorithms for detecting obstacles, human hands, and affective touch gestures. The computational requirements of the proposed architecture are in line with the capabilities of a small microcontroller
Deep learning approaches have been used to perform classification in several applications with high-dimensional input data. In this paper, we investigate the potential for deep learning for classifying affective touch on robotic skin in a social setting. Three models are considered, a convolutional…