Toward Universal and Interpretable World Models for Open-ended Learning Agents
Fuente:
arXiv
Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912073064120320 |
|---|---|
| author | Da Costa, Lancelot |
| author_facet | Da Costa, Lancelot |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_18676 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Toward Universal and Interpretable World Models for Open-ended Learning Agents Da Costa, Lancelot Artificial Intelligence Multiagent Systems Neurons and Cognition 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. |
| title | Toward Universal and Interpretable World Models for Open-ended Learning Agents |
| topic | Artificial Intelligence Multiagent Systems Neurons and Cognition |
| url | https://arxiv.org/abs/2409.18676 |