Publications

Learning in Hybrid Active Inference Models

Published in Communications in Computer and Information Science, vol 2193, 2024

A novel hierarchical hybrid active inference agent in which a high-level discrete planner is formed from emergent descriptions discovered by a recurrent switching linear dynamical system generative model.

Collis, P., Singh, R., Kinghorn, P.F., Buckley, C.L. (2025). Learning in Hybrid Active Inference Models. In: Buckley, C.L., et al. Active Inference. IWAI 2024. Communications in Computer and Information Science, vol 2193. Springer, Cham.

Hybrid Recurrent Models Support Emergent Descriptions for Hierarchical Planning and Control

Published in arXiv preprint, 2024

A novel hierarchical hybrid active inference agent in which a high-level discrete planner is formed from emergent descriptions discovered by a recurrent switching linear dynamical system generative model.

Collis, P., Singh, R., Kinghorn, P.F., Buckley, C.L. (2024). Hybrid Recurrent Models Support Emergent Descriptions for Hierarchical Planning and Control. arXiv preprint.

Understanding Tool Discovery and Tool Innovation Using Active Inference

Published in Communications in Computer and Information Science, vol 1915, 2024

An articulation of the distinction between tool discovery and tool innovation under the formalism of active inference

Collis, P., Kinghorn, P.F., Buckley, C.L. (2024). Understanding Tool Discovery and Tool Innovation Using Active Inference. In: Buckley, C.L., et al. Active Inference. IWAI 2023. Communications in Computer and Information Science, vol 1915. Springer, Cham.