Scaling active inference

Tschantz, Alexander, Baltieri, Manuel, Seth, Anil K and Buckley, Christopher L (2020) Scaling active inference. IEEE World Congress On Computational Intelligence: The International Joint Conference on Neural Networks (IJCNN), Glasgow, July 19 - 24th 2020. Published in: 2020 International Joint Conference on Neural Networks (IJCNN). IEEE ISSN 2161-4393 ISBN 9781728169279

[img] PDF - Accepted Version
Download (415kB)


In reinforcement learning (RL), agents often operate in partially observed and uncertain environments. Model-based RL suggests that this is best achieved by learning and exploiting a probabilistic model of the world. ‘Active inference’ is an emerging normative framework in cognitive and computational neuroscience that offers a unifying account of how biological agents achieve this. On this framework, inference, learning and action emerge from a single imperative to maximize the Bayesian evidence for a niched model of the world. However, implementations of this process have thus far been restricted to low-dimensional and idealized situations. Here, we present a working implementation of active inference that applies to high-dimensional tasks, with proof-of-principle results demonstrating efficient exploration and an order of magnitude increase in sample efficiency over strong model-free baselines. Our results demonstrate the feasibility of applying active inference at scale and highlight the operational homologies between active inference and current model-based approaches to RL.

Item Type: Conference Proceedings
Schools and Departments: School of Engineering and Informatics > Informatics
SWORD Depositor: Mx Elements Account
Depositing User: Mx Elements Account
Date Deposited: 15 Jun 2020 11:22
Last Modified: 29 Sep 2020 13:45

View download statistics for this item

📧 Request an update