Experiments

V15: Temporal Memory

Addition: Two exponential-moving-average memory channels storing slow statistics of the pattern's history. Oscillating resource patches reward anticipation.

Result: Evolution selected for longer memory in 2/3 seeds — memory decay constants decreased 6x. Under bottleneck pressure, $\intinfo$ stress response doubled (0.231 to 0.434). Peak robustness 1.070.

Temporal integration is fitness-relevant. This was the only substrate addition evolution consistently selected for. Memory channels help prediction (~12x vs V13) but don't break the sensory-motor wall.

Source code

v15_substrate.py — EMA memory channels
v15_evolution.py — Evolution with memory tracking
v15_gpu_run.py — GPU runner
v15_experiments.py — Measurement re-runs on V15