Older News

2024

  • New preprint “Do Agents Dream of Electric Sheep?: Improving Generalization in Reinforcement Learning through Generative Learning”. You can download the preprint here.

  • New preprint: “Dynamics of Moral Behavior in Heterogeneous Populations of Learning Agents”. You can download the preprint here.

  • New preprint: “Information-Theoretic State Variable Selection for Reinforcement Learning”. You can download the preprint here.

  • Our paper “Reinforcement Learning for Generative AI: State of the Art, Opportunities and Open Research Challenges” has been accepted for publication in the Journal of Artificial Intelligence Research (JAIR). You can download the paper here.

  • New preprint “Learning Machine Morality through Experience and Interaction”. You can download the preprint here.

  • New preprint “(Ir)rationality in AI: State of the Art, Research Challenges and Open Questions”. You can download the preprint here.

2023

  • New preprint “Tree Search in DAG Space with Model-based Reinforcement Learning for Causal Discovery”. You can download the preprint here.

  • New preprint “Reinforcement Learning for Generative AI: State of the Art, Opportunities and Open Research Challenges”. You can download the preprint here.

  • Marta Emili Garcia-Segura and Melvin Mammen joined the lab as new PhD students in September 2023. Welcome!

  • New preprint “CoMIX: A Multi-agent Reinforcement Learning Training Architecture for Efficient Decentralized Coordination and Independent Decision Making”. You can download the preprint here.

  • Our work on measuring AI creativity has been covered in this ACM News article.

  • New preprint “Augmented Modular Reinforcement Learning based on Heterogeneous Knowledge” discussing a novel learning modular architecture based on reinforcement learning for processing and integrating multiple types of information (knowledge). You can download the article here.

  • Our paper “Modeling Moral Choices in Social Dilemmas with Multi-Agent Reinforcement” has been accepted for publication in the main research track of the 32nd International Joint Conference on Artificial Intelligence (IJCAI 2023). You can download the preprint of the paper here.

  • Article in The Atlantic citing our paper on the creativity of Large Language Models.

  • New preprint “On the Creativity of Large Language Models” discussing the problem of machine creativity in relation to LLMs. You can download the article here.

  • Victor-Alexandru Darvariu has passed his PhD viva with a thesis on “Learning to Optimise Networked Systems”. Well done Victor!

  • Our paper “CT-DQN: Control-Tutored Deep Reinforcement Learning” has been accepted for publication at the Learning for Dynamics and Control Conference (L4DC 2023). You can download the pre-print version of the paper here. The camera ready version of the paper will appear soon.

  • Our paper “Planning Spatial Networks with Monte Carlo Tree Search” has been accepted for publication in Proceedings of the Royal Society A. You can download the paper here.

  • Our paper “RLQ: Workload Allocation with Reinforcement Learning in Distributed Queues” has been accepted for publications in IEEE Transactions in Parallel and Distributed Systems. You can download the paper here.


Last updated: 25 June 2024.