{"slug": "mitigating-catastrophic-forgetting-with-physics-indexed-specialist-memory-the", "title": "Mitigating Catastrophic Forgetting with Physics-Indexed Specialist Memory: the Evolutionary Neuroplastic Agent", "summary": "A paper submitted to arXiv on 16 Nov 2026 by Blas Eugenio Vicco Zarate reports that the Evolutionary Neuroplastic Agent (ENA) reached a mean success rate of 83.2% across five test environments in a 30-replicate CartPole ablation. ENA evolves small neural networks without gradients, archives selected policies by detected dynamic regime, and retrieves them through Bayesian policy reuse to mitigate catastrophic forgetting in continual reinforcement learning. The authors state ENA adapted more slowly than PPO on CartPole and achieved lower returns than SAC on HalfCheetah, and that the evidence does not isolate gradient-free optimization as the cause of retention or establish superiority over other continual-learning methods.", "body_md": "# Computer Science > Machine Learning\n\n  [Submitted on 16 Nov 2026]\n\n# Title:Mitigating Catastrophic Forgetting with Physics-Indexed Specialist Memory: the Evolutionary Neuroplastic Agent\n\n[View PDF](http://arxiv.org/pdf/2611.21598v1)\n\n[HTML (experimental)](https://arxiv.org/html/2611.21598v1)\n\nAbstract: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.\n    \n\n## Submission history\n\nFrom: Blas Eugenio Vicco Zarate [\n[view email](http://arxiv.org/show-email/03d33920/2611.21598)]\n\n**[v1]** Mon, 16 Nov 2026 18:58:20 UTC (243 KB)\n\n### Additional Features\n\n### Current browse context:\n\ncs.LG\n\n### References & Citations\n\nLoading...\n\n# Bibliographic and Citation Tools\n\nBibliographic Explorer \n\n*(*[What is the Explorer?](https://info.arxiv.org/labs/showcase.html#arxiv-bibliographic-explorer))\nConnected Papers \n\n*(*[What is Connected Papers?](https://www.connectedpapers.com/about))\nLitmaps \n\n*(*[What is Litmaps?](https://www.litmaps.co/))\nscite Smart Citations \n\n*(*[What are Smart Citations?](https://www.scite.ai/))\n# Code, Data and Media Associated with this Article\n\nalphaXiv \n\n*(*[What is alphaXiv?](https://alphaxiv.org/))\nCatalyzeX Code Finder for Papers \n\n*(*[What is CatalyzeX?](https://www.catalyzex.com))\nDagsHub \n\n*(*[What is DagsHub?](https://dagshub.com/))\nGotit.pub \n\n*(*[What is GotitPub?](http://gotit.pub/faq))\nHugging Face \n\n*(*[What is Huggingface?](https://huggingface.co/huggingface))\nScienceCast \n\n*(*[What is ScienceCast?](https://sciencecast.org/welcome))\n# Demos\n\n# Recommenders and Search Tools\n\nInfluence Flower \n\n*(*[What are Influence Flowers?](https://influencemap.cmlab.dev/))\nCORE Recommender \n\n*(*[What is CORE?](https://core.ac.uk/services/recommender))\nIArxiv Recommender\n\n*(*[What is IArxiv?](https://iarxiv.org/about))\n# arXivLabs: experimental projects with community collaborators\n\narXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.\n\nBoth individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.\n\nHave an idea for a project that will add value for arXiv's community? [**Learn more about arXivLabs**](https://info.arxiv.org/labs/index.html).", "url": "https://wpnews.pro/news/mitigating-catastrophic-forgetting-with-physics-indexed-specialist-memory-the", "canonical_source": "http://arxiv.org/abs/2611.21598v1", "published_at": "2026-11-17 14:20:32+00:00", "updated_at": "2026-11-17 20:00:38.857431+00:00", "lang": "en", "topics": ["machine-learning", "ai-research", "neural-networks", "artificial-intelligence"], "entities": ["arXiv", "Evolutionary Neuroplastic Agent", "Blas Eugenio Vicco Zarate", "PPO", "SAC", "CartPole", "HalfCheetah"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/mitigating-catastrophic-forgetting-with-physics-indexed-specialist-memory-the", "markdown": "https://wpnews.pro/news/mitigating-catastrophic-forgetting-with-physics-indexed-specialist-memory-the.md", "text": "https://wpnews.pro/news/mitigating-catastrophic-forgetting-with-physics-indexed-specialist-memory-the.txt", "jsonld": "https://wpnews.pro/news/mitigating-catastrophic-forgetting-with-physics-indexed-specialist-memory-the.jsonld"}}