Personality Requires Struggle: Three Regimes of the Baldwin Effect in Neuroevolved Chess Agents

TL;DR

This study investigates how lifetime learning influences behavioral diversity in neuroevolved chess agents, revealing a reversal from diversity reduction to expansion over generations due to an imagination-driven feedback loop.

Contribution

It demonstrates that plasticity can initially compress but eventually expand behavioral variance in evolved agents, highlighting three distinct regimes of personality emergence in competitive environments.

Findings

Hebbian plasticity initially reduces variance, then increases it after 34 generations.

Agents develop distinct, reproducible behavioral signatures such as move choices and opening repertoires.

Three regimes—exploration, lottery, transparent—depend on opponent type and influence diversity.

Abstract

Can lifetime learning expand behavioral diversity over evolutionary time, rather than collapsing it? Prior theory predicts that plasticity reduces variance by buffering organisms against environmental noise. We test this in a competitive domain: chess agents with eight NEAT-evolved neural modules, Hebbian within-game plasticity, and a desirability-domain signal chain with imagination. Across 10~seeds per Hebbian condition, a variance crossover emerges: Hebbian ON starts with lower cross-seed variance than OFF, then surpasses it at generation~34. The crossover trend is monotonic (\r{ho} = 0.91, p < 10^{-6): plasticity's effect on behavioral variance reverses over evolutionary time, initially compressing diversity (consistent with prior predictions) then expanding it as evolved Perception differences are amplified through imagination -- a feedback loop that mutation alone cannot sustain. The result is structured behavioral divergence: evolved agents select different moves on the same positions (62\% disagreement), develop distinct opening repertoires, piece preferences, and game lengths. These are not different sampling policies -- they are reproducible behavioral signatures (ICC > 0.8) with interpretable signal chain configurations. Three regimes appear depending on opponent type: exploration (Hebbian ON, heterogeneous opponent), lottery (Hebbian OFF, elitism lock-in), and transparent (same-model opponent, brain self-erasure). The transparent regime generates a falsifiable prediction: self-play systems may systematically suppress behavioral diversity by eliminating the heterogeneity that personality requires. \textbf{Keywords: Baldwin Effect, neuroevolution, NEAT, Hebbian learning, chess, cognitive architecture, personality emergence, imagination