Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2404.06529 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929308244639744 |
|---|---|
| author | Bayer, Caleidgh Smith, Robert J. Heywood, Malcolm I. |
| author_facet | Bayer, Caleidgh Smith, Robert J. Heywood, Malcolm I. |
| contents | The navigation of complex labyrinths with tens of rooms under visual partially observable state is typically addressed using recurrent deep reinforcement learning architectures. In this work, we show that navigation can be achieved through the emergent evolution of a simple Braitentberg-style heuristic that structures the interaction between agent and labyrinth, i.e. complex behaviour from simple heuristics. To do so, the approach of tangled program graphs is assumed in which programs cooperatively coevolve to develop a modular indexing scheme that only employs 0.8\% of the state space. We attribute this simplicity to several biases implicit in the representation, such as the use of pixel indexing as opposed to deploying a convolutional kernel or image processing operators. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_06529 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Emergent Braitenberg-style Behaviours for Navigating the ViZDoom `My Way Home' Labyrinth Bayer, Caleidgh Smith, Robert J. Heywood, Malcolm I. Neural and Evolutionary Computing Artificial Intelligence The navigation of complex labyrinths with tens of rooms under visual partially observable state is typically addressed using recurrent deep reinforcement learning architectures. In this work, we show that navigation can be achieved through the emergent evolution of a simple Braitentberg-style heuristic that structures the interaction between agent and labyrinth, i.e. complex behaviour from simple heuristics. To do so, the approach of tangled program graphs is assumed in which programs cooperatively coevolve to develop a modular indexing scheme that only employs 0.8\% of the state space. We attribute this simplicity to several biases implicit in the representation, such as the use of pixel indexing as opposed to deploying a convolutional kernel or image processing operators. |
| title | Emergent Braitenberg-style Behaviours for Navigating the ViZDoom `My Way Home' Labyrinth |
| topic | Neural and Evolutionary Computing Artificial Intelligence |
| url | https://arxiv.org/abs/2404.06529 |