Inverse reinforcement learning as the algorithmic basis for theory of mind: current methods and open problems

J Ruiz-Serra, MS Harré - Algorithms, 2023 - mdpi.com
Theory of mind (ToM) is the psychological construct by which we model another's internal
mental states. Through ToM, we adjust our own behaviour to best suit a social context, and …

Open human-robot collaboration using decentralized inverse reinforcement learning

PS Suresh, S Jain, P Doshi, D Romeres - arXiv preprint arXiv:2410.01790, 2024 - arxiv.org
The growing interest in human-robot collaboration (HRC), where humans and robots
cooperate towards shared goals, has seen significant advancements over the past decade …

Online Inverse Reinforcement Learning with Learned Observation Model

S Arora, P Doshi, B Banerjee - Conference on Robot …, 2023 - proceedings.mlr.press
With the motivation of extending incremental inverse reinforcement learning (I2RL) to real-
world robotics applications with noisy observations as well as an unknown observation …

MVSA-Net: Multi-View State-Action Recognition for Robust and Deployable Trajectory Generation

E Asali, P Doshi, J Sun - arXiv preprint arXiv:2311.08393, 2023 - arxiv.org
The learn-from-observation (LfO) paradigm is a human-inspired mode for a robot to learn to
perform a task simply by watching it being performed. LfO can facilitate robot integration on …

[PDF][PDF] IRL for Restless Multi-Armed Bandits with Applications in Maternal and Child Health

G Jain, P Varakantham, H Xu, A Taneja, P Doshi… - teamcore.seas.harvard.edu
Public health practitioners often have the goal of monitoring patients and maximizing
patients' time spent in “favorable" or healthy states while being constrained to using limited …