arXiv Machine Learning October 3, 2026 By Eleni Nisioti, Andrea Cossu, Kathrin Korte, Sebastian Risi

Continual Reinforcement Learning with Neuroevolution

Read the original on arXiv Machine Learning →

The paper investigates continual reinforcement learning using neuroevolution, comparing evolution strategies (ES) and genetic algorithms (GAs) across diverse environments and network sizes. ES consistently achieves a better balance between stability and plasticity, while GAs are more plastic but forget more. The authors attribute this to ES finding wider neighborhoods in weight space, with overlap between consecutive tasks correlating with the stability-plasticity trade‑off, and note that common RL plasticity issues do not transfer to neuroevolution.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv AI

Jun 10

Beyond Single-Model Optimization: Preserving Plasticity in Continual Reinforcement Learning

arXiv:2604. 15414v2 Announce Type: replace-cross Abstract: Continual reinforcement learning must balance retention with adaptation, yet many methods still rely on \emph{single-model preservation}, committing to one evolving policy as the main reusable solution across tasks.

By Lute Lillo, Nick Cheney

agents diffusion reinforcement-learning

arXiv Machine Learning

Aug 17

Continual Evolution Strategies in Control Tasks

arXiv:2608. 13600v1 Announce Type: cross Abstract: We study Evolution Strategies (ES) for continual control, where agents must adapt to changing tasks without forgetting previous ones.

By Nicola Pitzalis, Eleni Nisioti, Antonio Carta, Davide Bacciu, Andrea Cossu

agents robotics

arXiv AI

Jun 2

Task diversity produces systematic transfer but inhibits continual reinforcement learning

arXiv:2606. 00880v1 Announce Type: cross Abstract: Continual reinforcement learning aims to produce agents that learn not only to improve at their current tasks but also to adapt as task distributions change.

By Purab Seth, Neil Shah, Kunal Jha, Samuel J. Gershman, Max Kleiman-Weiner, Wilka Carvalho

agents reinforcement-learning benchmarks

arXiv Machine Learning

Aug 26

Dimensionless Controls of Plasticity Under Alternating Tasks: From Evolutionary Biology to Continual Learning

arXiv:2608.23889v1 Announce Type: cross Abstract: Plasticity under changing environments is central to both evolutionary biology and continual learning. Motivated by recent work on genotype--phenotyp...

By Owen Skriloff

arXiv Machine Learning

Aug 11

Matching Accuracy, Different Geometry: Evolution Strategies vs GRPO in LLM Post-Training

arXiv:2604. 01499v2 Announce Type: replace Abstract: Evolution Strategies (ES) have emerged as a scalable gradient-free alternative to reinforcement learning based LLM fine-tuning, but it remains unclear whether comparable task performance implies comparable solutions in parameter space.

By William Hoy, Binxu Wang, Xu Pan

llms reinforcement-learning fine-tuning

arXiv Machine Learning

Aug 3

NeuroSynth: A Biologically Inspired Continual Reinforcement Learning Architecture for Mitigating Catastrophic Forgetting

arXiv:2607. 28663v1 Announce Type: cross Abstract: Artificial Intelligence (AI) systems often perform well on isolated tasks but struggle under continual learning conditions, where training on new tasks can overwrite previously acquired knowledge, a failure mode known as catastrophic forgetting.

By Yash Kini

reinforcement-learning efficiency

One email a morning, machine-written

Related stories

Beyond Single-Model Optimization: Preserving Plasticity in Continual Reinforcement Learning

Continual Evolution Strategies in Control Tasks

Task diversity produces systematic transfer but inhibits continual reinforcement learning

Dimensionless Controls of Plasticity Under Alternating Tasks: From Evolutionary Biology to Continual Learning

Matching Accuracy, Different Geometry: Evolution Strategies vs GRPO in LLM Post-Training

NeuroSynth: A Biologically Inspired Continual Reinforcement Learning Architecture for Mitigating Catastrophic Forgetting