Control of Cellular Automata by Moving Agents with Reinforcement Learning
On the map: Deep reinforcement learning methods → Deep RL algorithms and representations
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Deep RL algorithms and representations, one of 15 directions in Deep reinforcement learning methods. Builds on 0 of its 4 references that are in the map. First posted on arXiv 11 Apr 2026.
Builds on
0 of 4 references.
No references here yet.
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026The Artificial Experimentalist: Discovery and Control of Self-Organizing Phenomena with Autotelic Reinforcement Learning
- 2025Automata-Conditioned Cooperative Multi-Agent Reinforcement Learning
- 2018PRIMAL: Pathfinding via Reinforcement and Imitation Multi-Agent Learning
- 2024Emergence of Implicit World Models from Mortal Agents
- 2025Provably Correct Automata Embeddings for Optimal Automata-Conditioned Reinforcement Learning
- 2026Hidden States as Value Gradients: The Pontryagin Structure of Recurrent Policies
- 2025Illuminating the Three Dogmas of Reinforcement Learning under Evolutionary Light
- 2024Compositional Automata Embeddings for Goal-Conditioned Reinforcement Learning