Discovering Sensorimotor Agency in Cellular Automata using Diversity Search

arXiv:2402.10236 · cs.MA, cs.AI, cs.LG · Submitted 2024-02-14 · Read on arXiv

cs.MA, cs.AI, cs.LG

Submitted: 2024-02-14

Updated: 2024-02-14

Code: https://github.com/flowersteam/sensorimotor-lenia-search

Project page: https://developmentalsystems.org/sensorimotor-lenia-companion

Terminology

• Robustness — 69× in this paper · explained in 5 episodes
• Generalization — 34× in this paper · explained in 13 episodes
• Ablation — 24× in this paper · explained in 1 episode
• Ablation Studies — 3× in this paper · explained in 1 episode
• Adaptivity — 3× in this paper · explained in 1 episode
• Chaotic Dynamics — 2× in this paper · explained in 2 episodes
• Intrinsically Motivated Goal Exploration Process — 2× in this paper
• Loss Function — 2× in this paper · explained in 2 episodes
• Reinforcement Learning — 2× in this paper · explained in 4 episodes
• Active Learning — 1× in this paper · explained in 6 episodes
• Adam — 1× in this paper · explained in 2 episodes
• Agent Interactions — 1× in this paper · explained in 1 episode
• Benchmark — 1× in this paper · explained in 2 episodes
• Local Optimization — 1× in this paper · explained in 2 episodes

Sources

• Paired Open-Ended Trailblazer (POET): Endlessly Generating Increasingly Complex and Diverse Learning Environments and Their Solutions
• Solving Rubik's Cube with a Robot Hand
• Emergent Tool Use From Multi-Agent Autocurricula
• Open-Ended Learning Leads to Generally Capable Agents
• Emergent Complexity via Multi-Agent Competition
• WebGPT: Browser-assisted question-answering with human feedback
• Toolformer: Language Models Can Teach Themselves to Use Tools

Related papers

• Highway Congestion Reduction through Reinforcement Learning Based Eulerian Headway Control
• You Only Align Once: Propagating Cooperative Behaviors in Multi-Agent Systems through Seed Agents
• Deny Without Disabling: Authorization-Paired Evaluation and Control for Multi-Agent Systems
• MA-SAPO: Multi-Agent Reasoning for Score-Aware Prompt Optimization
• PeroMAS: A Multi-agent System of Perovskite Material Discovery
• StitchCUDA: An Automated Multi-Agents End-to-End GPU Programing Framework with Rubric-based Agentic Reinforcement Learning