Durable experiment record · Local core code · curated results

Deep Universal Reinforcement Learning

GT and diagrammatic-backpropagation ablations for coalgebraic RL losses.

5 code surfaces0 frozen runs2 code packagescatagi-deep-url

Experimental contract

What this family tests

thirty-run controlled comparison

  • Thirty-run base learner comparison
  • Geometric Transformer structural-loss ablation
  • Diagrammatic-backpropagation residual ablation
  • Return, residual, and graph-smoothness comparison

Book-to-code crosswalk

The highlighted Experiment cards covered here

Implementation map

From entry point to source surface

Start here

These concrete files are selected from the complete registered source surface to orient the reader.

  • runner · staged-not-publicdeep-url-archive:run_synthetic_mdp_ablation.pyLocate this file in the curated companion packet; no public download is currently offered.
  • runner · staged-not-publicdeep-url-archive:run_synthetic_mdp_loop.pyLocate this file in the curated companion packet; no public download is currently offered.
  • runner · staged-not-publicdeep-url-archive:report_synthetic_mdp_ablation.pyLocate this file in the curated companion packet; no public download is currently offered.
  • runner · staged-not-publicdeep-url-archive:report_synthetic_mdp_metrics.pyLocate this file in the curated companion packet; no public download is currently offered.

Author-declared entry points

  • GT_RL_Coalgebra experiment scripts

Resolved code

runner · 5
  • deep-url-archive:report_synthetic_mdp_ablation.py
  • deep-url-archive:report_synthetic_mdp_metrics.py
  • deep-url-archive:run_synthetic_mdp_ablation.py
  • deep-url-archive:run_synthetic_mdp_loop.py
  • deep-url-archive:synthetic_mdp_bridge.py

Evidence record

Artifacts and frozen runs

Result artifacts

  • thirty-run return and residual summaries

Run records

No run-level packet is registered. The family retains code-level provenance, but public run reproduction still requires curation.

Evidence boundary

Lower structural residual or graph smoothness is not proof that a coalgebra morphism was learned.

This registry links the experiments reported by the three books to their executable or archived code surfaces. A code link establishes traceability, not independent reproduction, correctness, or support for a claim beyond the experiment's stated boundary.