Mind the gap: Challenges of deep learning approaches to theory of mind

J Aru, A Labash, O Corcoll, R Vicente - Artificial Intelligence Review, 2023 - Springer
Abstract Theory of Mind (ToM) is an essential ability of humans to infer the mental states of
others. Here we provide a coherent summary of the potential, current progress, and …

Theory of mind as intrinsic motivation for multi-agent reinforcement learning

I Oguntola, J Campbell, S Stepputtis… - arXiv preprint arXiv …, 2023 - arxiv.org
The ability to model the mental states of others is crucial to human social intelligence, and
can offer similar benefits to artificial agents with respect to the social dynamics induced in …

A cognitive framework for delegation between error-prone AI and human agents

A Fuchs, A Passarella, M Conti - 2022 IEEE International …, 2022 - ieeexplore.ieee.org
With humans interacting with AI-based systems at an increasing rate, it is necessary to
ensure the artificial systems are acting in a manner which reflects understanding of the …

Multi-agent reinforcement learning for fast-timescale demand response of residential loads

V Mai, P Maisonneuve, T Zhang, H Nekoei, L Paull… - Machine Learning, 2024 - Springer
To integrate high amounts of renewable energy resources, electrical power grids must be
able to cope with high amplitude, fast timescale variations in power generation. Frequency …

Boss: A benchmark for human belief prediction in object-context scenarios

J Duan, S Yu, N Tan, L Yi, C Tan - arXiv preprint arXiv:2206.10665, 2022 - arxiv.org
Humans with an average level of social cognition can infer the beliefs of others based solely
on the nonverbal communication signals (eg gaze, gesture, pose and contextual …

Cogment: Open source framework for distributed multi-actor training, deployment & operations

AI Redefined, SK Gottipati, S Kurandwad… - arXiv preprint arXiv …, 2021 - arxiv.org
Involving humans directly for the benefit of AI agents' training is getting traction thanks to
several advances in reinforcement learning and human-in-the-loop learning. Humans can …

An Internet-assisted Dixit-playing AI

D Vatsakis, P Mavromoustakos-Blom… - Proceedings of the 17th …, 2022 - dl.acm.org
This paper investigates the development of an Artificial Intelligence (AI) agent which plays
the voting phase of the board game Dixit. Given a set of open cards and a lexical “hint” …

Autonomous Vehicle Decision-Making Framework for Considering Malicious Behavior at Unsignalized Intersections

Q Li, J Hua, Q Sun - arXiv preprint arXiv:2409.17162, 2024 - arxiv.org
In this paper, we propose a Q-learning based decision-making framework to improve the
safety and efficiency of Autonomous Vehicles when they encounter other maliciously …

A theory-of-mind game for the early detection of frontotemporal dementia

M Bekooy, DD Berendsen, M Dierikx… - … on Interactive Digital …, 2023 - Springer
People with behavioural variant frontotemporal dementia (bvFTD) struggle with social
interactions and the recognition of emotions. Currently, questionnaires with pen and paper …

Generative Artificial Intelligence for Behavioral Intent Prediction

W Mannering, N Ford, JJ Harsono… - Proceedings of the …, 2024 - escholarship.org
Theory of mind is an essential ability for complex social interaction and collaboration.
Researchers in cognitive science and psychology have previously sought to integrate theory …