Saved in:
Bibliographic Details
Main Author: Matthew, Fearne
Format: Recurso digital
Language:
Published: Zenodo 2026
Online Access:https://doi.org/10.5281/zenodo.18717202
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • <p>We present DigiSoup, a zero-training agent that uses thermodynamic perception and bio-inspired heuristics to play multi-agent social dilemmas on DeepMind's Melting Pot benchmark. DigiSoup<br>  uses no neural networks, no reward optimisation, and no training of any kind — actions are selected by a stack of priority rules driven by entropy gradients, temporal growth rates, and    <br>  spatial memory, implemented in approximately 350 lines of NumPy.                                                                                                                            </p> <p>  Despite this simplicity, DigiSoup outperforms DeepMind's trained reinforcement learning baselines in aggregate on Clean Up — a complex public goods dilemma requiring collective action —<br>  scoring 22% above ACB and 46% above VMPO across 9 scenarios (30 episodes each, 95% confidence intervals reported). On CU_7, just two DigiSoup focal agents among seven players score 234.00<br>  versus ACB's 120.41 (+94%).</p> <p>  The key mechanism is a thermodynamic depletion signal: when the entropy growth rate drops to zero (dS/dt ≤ 0), the agent infers that the shared resource is depleted and diverts to public<br>  goods maintenance — without any reward signal indicating that cleaning is beneficial.</p> <p>  Code and full results: https://github.com/matthewfearne/digisoup</p>