Learning from suboptimal demonstration via self-supervised reward regression

L Chen, R Paleja, M Gombolay - Conference on robot …, 2021 - proceedings.mlr.press
Abstract Learning from Demonstration (LfD) seeks to democratize robotics by enabling non-
roboticist end-users to teach robots to perform a task by providing a human demonstration …

New scheduling approach using reinforcement learning for heterogeneous distributed systems

AI Orhean, F Pop, I Raicu - Journal of Parallel and Distributed Computing, 2018 - Elsevier
Computer clusters, cloud computing and the exploitation of parallel architectures and
algorithms have become the norm when dealing with scientific applications that work with …

Robotic assistance in the coordination of patient care

M Gombolay, XJ Yang, B Hayes… - … Journal of Robotics …, 2018 - journals.sagepub.com
We conducted a study to investigate trust in and dependence upon robotic decision support
among nurses and doctors on a labor and delivery floor. There is evidence that suggestions …

Deployment and evaluation of a flexible human–robot collaboration model based on AND/OR graphs in a manufacturing environment

PK Murali, K Darvish, F Mastrogiovanni - Intelligent Service Robotics, 2020 - Springer
The Industry 4.0 paradigm promises shorter development times, increased ergonomy,
higher flexibility and resource efficiency in manufacturing environments. Collaborative …

Joint goal and strategy inference across heterogeneous demonstrators via reward network distillation

L Chen, R Paleja, M Ghuy, M Gombolay - Proceedings of the 2020 ACM …, 2020 - dl.acm.org
Reinforcement learning (RL) has achieved tremendous success as a general framework for
learning how to make decisions. However, this success relies on the interactive hand-tuning …

Teaching robots social autonomy from in situ human guidance

E Senft, S Lemaignan, PE Baxter, M Bartlett… - Science Robotics, 2019 - science.org
Striking the right balance between robot autonomy and human control is a core challenge in
social robotics, in both technical and ethical terms. On the one hand, extended robot …

Collaborative planning with encoding of users' high-level strategies

J Kim, C Banks, J Shah - Proceedings of the AAAI Conference on …, 2017 - ojs.aaai.org
The generation of near-optimal plans for multi-agent systems with numerical states and
temporal actions is computationally challenging. Current off-the-shelf planners can take a …

Interpretable and personalized apprenticeship scheduling: Learning interpretable scheduling policies from heterogeneous user demonstrations

R Paleja, A Silva, L Chen… - Advances in neural …, 2020 - proceedings.neurips.cc
Resource scheduling and coordination is an NP-hard optimization requiring an efficient
allocation of agents to a set of tasks with upper-and lower bound temporal and resource …

Learning skill training schedules from domain experts for a multi-patient multi-robot rehabilitation gym

B Adhikari, VR Bharadwaj, BA Miller… - … on Neural Systems …, 2023 - ieeexplore.ieee.org
A robotic gym with multiple rehabilitation robots allows multiple patients to exercise
simultaneously under the supervision of a single therapist. The multi-patient training …

Sheet-metal production scheduling using AlphaGo Zero

A Rinciog, C Mieth, PM Scheikl… - Proceedings of the …, 2020 - repo.uni-hannover.de
This work investigates the applicability of a reinforcement learning (RL) approach,
specifically AlphaGo Zero (AZ), for optimizing sheet-metal (SM) production schedules with …