Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2411.12304 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929597750181888 |
|---|---|
| author | Horibe, Kazuya Yoshida, Naoto |
| author_facet | Horibe, Kazuya Yoshida, Naoto |
| contents | We discuss the possibility of world models and active exploration as emergent properties of open-ended behavior optimization in autonomous agents. In discussing the source of the open-endedness of living things, we start from the perspective of biological systems as understood by the mechanistic approach of theoretical biology and artificial life. From this perspective, we discuss the potential of homeostasis in particular as an open-ended objective for autonomous agents and as a general, integrative extrinsic motivation. We then discuss the possibility of implicitly acquiring a world model and active exploration through the internal dynamics of a network, and a hypothetical architecture for this, by combining meta-reinforcement learning, which assumes domain adaptation as a system that achieves robust homeostasis. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_12304 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Emergence of Implicit World Models from Mortal Agents Horibe, Kazuya Yoshida, Naoto Neural and Evolutionary Computing Machine Learning We discuss the possibility of world models and active exploration as emergent properties of open-ended behavior optimization in autonomous agents. In discussing the source of the open-endedness of living things, we start from the perspective of biological systems as understood by the mechanistic approach of theoretical biology and artificial life. From this perspective, we discuss the potential of homeostasis in particular as an open-ended objective for autonomous agents and as a general, integrative extrinsic motivation. We then discuss the possibility of implicitly acquiring a world model and active exploration through the internal dynamics of a network, and a hypothetical architecture for this, by combining meta-reinforcement learning, which assumes domain adaptation as a system that achieves robust homeostasis. |
| title | Emergence of Implicit World Models from Mortal Agents |
| topic | Neural and Evolutionary Computing Machine Learning |
| url | https://arxiv.org/abs/2411.12304 |