Personality Requires Struggle: Three Regimes of the Baldwin Effect in Neuroevolved Chess Agents
Summary: arXiv:2604.03565v1 Announce Type: new
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 (ρ = 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.
Key Findings
- Baldwin Effect: Demonstrates how lifetime learning can affect behavioral diversity in artificially evolved systems.
- Neuroevolution: Utilizes NEAT (NeuroEvolution of Augmenting Topologies) to create neural networks for chess agents.
- Hebbian Learning: Investigates the role of Hebbian plasticity within the game, affecting variance in behavior.
- Behavioral Divergence: Reveals that agents develop unique strategies leading to significant differences in gameplay.
- Three Regimes of Play: Identifies distinct behavioral regimes—exploration, lottery, and transparent—based on opponent type.
Conclusion
This study highlights the complex interplay between learning mechanisms and behavioral diversity in neuroevolved chess agents. It challenges existing theories about plasticity and variance, suggesting that initial constraints may lead to greater diversity over evolutionary time. The implications extend beyond chess to broader fields such as artificial intelligence and cognitive architecture, providing insights into how personality and individuality can emerge in computational systems.
Keywords: Baldwin Effect, neuroevolution, NEAT, Hebbian learning, chess, cognitive architecture, personality emergence, imagination.