Mitigating Catastrophic Forgetting with Physics-Indexed Specialist Memory: the Evolutionary Neuroplastic Agent
[Uczenie maszynowe] Autorzy: Blas Eugenio Vicco Zarate, Miguel Hernán Vicco
Continual reinforcement learning requires adaptation to changing conditions while preserving performance under previously encountered dynamics. It was investigated whether specialists generated by evolutionary search can provide a reusable memory when combined with environment detection and failure-driven search. The Evolutionary Neuroplastic Agent (ENA) evolves small neural networks without gradients, archives selected policies by detected dynamic regime, and retrieves them through Bayesian policy reuse. The architecture was evaluated in non-stationary CartPole and HalfCheetah environments. In the 30-replicate CartPole ablation, the complete architecture achieved a mean success rate of 83.2% across the five test environments. Among variants that learned the harder CartPole environments, the complete architecture showed the most consistent retention. A selection ablation also showed tha…
- Kategoria arxiv
- cs.LG
- Kategoria
- Uczenie maszynowe