Publications

Harms from Increasingly Agentic Algorithmic Systems

Alan Chan, Rebecca Salganik, Alva Markelius, Chris Pang, Nitarshan Rajkumar, Dmitrii Krasheninnikov, Lauro Langosco, Zhonghao He, Yawen Duan, Micah Carroll, Michelle Lin, Alex Mayhew, Katherine Collins, Maryam Molamohammadi, John Burden, Wanru Zhao, Shalaleh Rismani, Konstantinos Voudouris, Umang Bhatt, Adrian Weller, David Krueger, Tegan Maharaj, arXiv preprint arXiv:2302.10329

Evaluating Object Permanence in Embodied Agents Using the Animal-AI Environment

Konstantinos Voudouris, Niall Donnelly, Danaja Rutar, Ryan Burnell, John Burden, José Hernández-Orallo, Lucy G Cheke

How General-purpose is a Language Model? Usefulness and Safety With Human Prompters in the Wild

PAM Casares, BS Loe, J Burden, S Ó hÉigeartaigh, J Hernández-Orallo
Proceedings of the AAAI Conference on Artificial Intelligence 36 (5), 5295-5303

Beyond the Imitation Game: Quantifying and Extrapolating the Capabilities of Language Models

A Srivastava, A Rastogi, A Rao, AAM Shoeb, A Abid, A Fisch, AR Brown, et al., arXiv preprint arXiv:2206.04615

Not a Number: Identifying Instance Features for Capability-Oriented Evaluation

Ryan Burnell, John Burden, Danaja Rutar, Konstantinos Voudouris, Lucy Cheke, José Hernández-Orallo, 2022, Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, IJCAI-22

Oases of Cooperation: An Empirical Evaluation of Reinforcement Learning in the Iterated Prisoner's Dilemma.

Peter Barnett, John Burden, 2022, SafeAI@ AAAI

Safety-driven design of machine learning for sepsis treatment

Yan Jia, Tom Lawton, John Burden, John McDermid, Ibrahim Habli, In Journal of Biomedical Informatics, Volume 117, 2021,103762, ISSN 1532-0464,

Negative Side Effects and AI Agent Indicators: Experiments in SafeLife

John Burden, José Hernández-Orallo, Seán Ó hÉigeartaigh, SafeAI@AAAI 2021

Exploring AI Safety in Degrees: Generality, Capability and Control

John Burden and José Hernández-Orallo, SafeAI@AAAI2020

Latent Property State Abstraction For Reinforcement Learning

John Burden, Sajjad Kamali Siahroudi, Daniel Kudenko. In Workshop on Adaptive Learning Agents (ALA) at AAMAS 2021

Safe Reinforcement Learning for Sepsis Treatment.

Yan Jia. John Burden, Tom Lawton, Ibrahim Habli (2020) In: 8th IEEE International Conference on Healthcare Informatics

Uniform State Abstraction For Reinforcement Learning

John Burden and Daniel Kudenko. In proceedings of the 24th European Conference on Artificial Intelligence (ECAI 2020)

Using Uniform State Abstractions For Reward Shaping With Reinforcement Learning

John Burden and Daniel Kudenko. In Workshop on Adaptive Learning Agents (ALA) at the Federated AI Meeting. 2018