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.
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.
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.
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.
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...
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.
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.
arXiv:2606. 20858v2 Announce Type: replace Abstract: The temporal structure of reward composition in reinforcement learning (RL) is typically hand-designed and held fixed throughout training, leaving the progression of motivational priorities largely unexplored.
arXiv:2505. 18347v3 Announce Type: replace-cross Abstract: Continual reinforcement learning (RL) concerns agents that are expected to learn continually, rather than converge to a policy that is then fixed for evaluation.
arXiv:2608. 01475v1 Announce Type: new Abstract: Neural networks that can grow or both grow and shrink during learning, referred to as growing neural networks and elastic neural networks, respectively, have recently been explored in offline continual learning with a particular focus on catastrophic forgetting.
arXiv:2608. 14634v1 Announce Type: new Abstract: Biological intelligence naturally prevents catastrophic forgetting through Complementary Learning Systems (CLS) theory, a macroscopic consolidation process driven at the local level by synaptic metaplasticity: the continuous, history-dependent neuromodulation of individual synapses.
We’ve discovered that evolution strategies (ES), an optimization technique that’s been known for decades, rivals the performance of standard reinforcement learning (RL) techniques on modern RL benchmarks (e. g.
arXiv:2608. 02508v1 Announce Type: new Abstract: Learning-based memory systems for self-evolving LLM agents face two tightly coupled challenges.