arXiv · 2611.21598
Mitigating Catastrophic Forgetting with Physics-Indexed Specialist Memory: the Evolutionary Neuroplastic Agent
Abstract
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 that the retrieval rule affected performance. In the evaluated sequences, ENA adapted more slowly than PPO on CartPole and achieved lower returns than SAC on HalfCheetah. The evidence concerns the complete architecture and does not isolate gradient-free optimization as the cause of retention or establish superiority over other continual-learning methods.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Blas Eugenio Vicco Zarate, Miguel Hernán Vicco. 2026-11-16. Mitigating Catastrophic Forgetting with Physics-Indexed Specialist Memory: the Evolutionary Neuroplastic Agent. https://searcharxiv.com/abs/2611.21598
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.