Theory of Mind abilities of Large Language Models in Human-Robot Interaction: An Illusion?
Large Language Models (LLMs) have shown exceptional generative abilities in various
natural language and generation tasks. However, possible anthropomorphization and …
natural language and generation tasks. However, possible anthropomorphization and …
Exploiting Unlabeled Data for Feedback Efficient Human Preference based Reinforcement Learning
Preference Based Reinforcement Learning has shown much promise for utilizing human
binary feedback on queried trajectory pairs to recover the underlying reward model of the …
binary feedback on queried trajectory pairs to recover the underlying reward model of the …
A mental model based theory of trust
Handling trust is one of the core requirements for facilitating effective interaction between the
human and the AI agent. Thus, any decision-making framework designed to work with …
human and the AI agent. Thus, any decision-making framework designed to work with …
Data Driven Reward Initialization for Preference based Reinforcement Learning
M Verma, S Kambhampati - arXiv preprint arXiv:2302.08733, 2023 - arxiv.org
Preference-based Reinforcement Learning (PbRL) methods utilize binary feedback from the
human in the loop (HiL) over queried trajectory pairs to learn a reward model in an attempt …
human in the loop (HiL) over queried trajectory pairs to learn a reward model in an attempt …
A State Augmentation based approach to Reinforcement Learning from Human Preferences
M Verma, S Kambhampati - arXiv preprint arXiv:2302.08734, 2023 - arxiv.org
Reinforcement Learning has suffered from poor reward specification, and issues for reward
hacking even in simple enough domains. Preference Based Reinforcement Learning …
hacking even in simple enough domains. Preference Based Reinforcement Learning …
Advice Conformance Verification by Reinforcement Learning agents for Human-in-the-Loop
Human-in-the-loop (HiL) reinforcement learning is gaining traction in domains with large
action and state spaces, and sparse rewards by allowing the agent to take advice from HiL …
action and state spaces, and sparse rewards by allowing the agent to take advice from HiL …
Computational Accounts of Trust in Human AI Interaction
Z Zahedi - 2023 - search.proquest.com
The growing presence of AI-driven systems in everyday life calls for the development of
efficient methods to facilitate interactions between humans and AI agents. At the heart of …
efficient methods to facilitate interactions between humans and AI agents. At the heart of …
Modeling, Engendering and Leveraging Trust in Human-Robot Interaction: A Mental Model Based Framework
Z Zahedi - Companion of the 2024 ACM/IEEE International …, 2024 - dl.acm.org
Trust between team members is a necessary part of any successful cooperation. Therefore,
in mixed human-robot teams, the robot must possess the ability to model, assess and …
in mixed human-robot teams, the robot must possess the ability to model, assess and …