Paper Detail

Mitigating Catastrophic Forgetting with Physics-Indexed Specialist Memory: the Evolutionary Neuroplastic Agent

Blas Eugenio Vicco Zarate, Miguel Hernán Vicco

arxiv Score 20.3

Published 2026-11-16 · First seen 2026-11-17

Research Track A · General AI

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.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
now
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@article{zarate2026mitigating,
  title = {Mitigating Catastrophic Forgetting with Physics-Indexed Specialist Memory: the Evolutionary Neuroplastic Agent},
  author = {Blas Eugenio Vicco Zarate and Miguel Hernán Vicco},
  year = {2026},
  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 pol},
  url = {https://arxiv.org/abs/2611.21598},
  keywords = {cs.LG, cs.AI, cs.NE},
  eprint = {2611.21598},
  archiveprefix = {arXiv},
}

Metadata

{}