Back to Search
Start Over
Toward Universal and Interpretable World Models for Open-ended Learning Agents
- Source :
- NeurIPS 2024 Workshop on Intrinsically Motivated Open-ended Learning (IMOL)
- Publication Year :
- 2024
-
Abstract
- We introduce a generic, compositional and interpretable class of generative world models that supports open-ended learning agents. This is a sparse class of Bayesian networks capable of approximating a broad range of stochastic processes, which provide agents with the ability to learn world models in a manner that may be both interpretable and computationally scalable. This approach integrating Bayesian structure learning and intrinsically motivated (model-based) planning enables agents to actively develop and refine their world models, which may lead to developmental learning and more robust, adaptive behavior.<br />Comment: 4 pages including appendix, 6 including appendix and references; 2 figures
Details
- Database :
- arXiv
- Journal :
- NeurIPS 2024 Workshop on Intrinsically Motivated Open-ended Learning (IMOL)
- Publication Type :
- Report
- Accession number :
- edsarx.2409.18676
- Document Type :
- Working Paper