Control of Cellular Automata by Moving Agents with Reinforcement Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915932193947648 |
|---|---|
| author | Bagnoli, Franco Sellami, Bassem Mouakher, Amira Yacoubi, Samira El |
| author_facet | Bagnoli, Franco Sellami, Bassem Mouakher, Amira Yacoubi, Samira El |
| contents | In this exploratory paper we introduce the problem of cognitive agents that learn how to modify their environment according to local sensing to reach a global goal. We concentrate on discrete dynamics (cellular automata) on a two-dimensional system. We show that agents may learn how to approximate their goal when the environment is passive, while this task becomes impossible if the environment follows an active dynamics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_10066 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Control of Cellular Automata by Moving Agents with Reinforcement Learning Bagnoli, Franco Sellami, Bassem Mouakher, Amira Yacoubi, Samira El Cellular Automata and Lattice Gases Systems and Control In this exploratory paper we introduce the problem of cognitive agents that learn how to modify their environment according to local sensing to reach a global goal. We concentrate on discrete dynamics (cellular automata) on a two-dimensional system. We show that agents may learn how to approximate their goal when the environment is passive, while this task becomes impossible if the environment follows an active dynamics. |
| title | Control of Cellular Automata by Moving Agents with Reinforcement Learning |
| topic | Cellular Automata and Lattice Gases Systems and Control |
| url | https://arxiv.org/abs/2604.10066 |