Stability-Plasticity Dilemma

Follow this topic Ask about this topic

Momentum

3 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 12

All topics

Continual Reinforcement Learning with Neuroevolution
Oct 1, 2026Eleni Nisioti, Andrea Cossu, Kathrin Korte +1Stability-Plasticity Dilemma Loss of Plasticity
IT University of Copenhagen · University of Pisa · Sakana AI
Generalized Residual Closure: General Learning Dynamics for Stability-Plasticity Compatibility
Sep 30, 2026Dongxu Li, Yinuo Zhang, Hongyu Zhang +1Stability-Plasticity Dilemma Continual Learning
Xi’an Jiaotong University · Xi’an University of Architecture and Technology
A Bellman Optimality Equation for Plasticity
Sep 11, 2026Jeremy Lucas, Doina PrecupStability-Plasticity Dilemma Reinforcement Learning
Mila – Quebec Artificial Intelligence Institute Montreal, Quebec, Canada
Functional compatibility as a determinant of persistent neural learning
Aug 23, 2026Hossein JavidniaStability-Plasticity Dilemma Continual Learning
School of Computing Dublin City University Dublin, Ireland
AdaHAT: Adaptive Hard Attention to the Task in Task-Incremental Learning
Aug 2, 2026Pengxiang Wang, Hongbo Bo, Jun Hong +2Stability-Plasticity Dilemma Incremental Learning
School of Mathematical Sciences, Peking University, Beijing, China · Population Health Sciences Institute, Newcastle University, Newcastle, UK · School of Engineering Mathematics and Technology, University of Bristol, Bristol, UK +1
Intrinsic-Noise Consolidation: A Doob-Barrier-Conditioned Diffusion Turns Analog Device Noise into a Continual-Learning Resource
Jul 8, 2026Gunner Levi HoweStability-Plasticity Dilemma Doob H-Transform
Janus-LoRA: A Balanced Low-Rank Adaptation for Continual Learning
May 27, 2026Cheng Chen, Pengpeng Zeng, Yuyu Guo +3Stability-Plasticity Dilemma Continual Learning
School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China · School of Computer Science and Technology, Tongji University, Shanghai, China · Independent Researcher +1
Balancing Plasticity and Stability with Fast and Slow Successor Features
May 25, 2026Raymond Chua, Doina Precup, Blake RichardsStability-Plasticity Dilemma Non-Stationary RL
School of Computer Science, McGill University, Montr´eal, Canada · Mila - Quebec Artificial Intelligence Institute, Montr´eal, QC, Canada · CIFAR Learning in Machines and Brains +3
Beyond Forgetting in Continual Medical Image Segmentation: A Comprehensive Benchmark Study
May 7, 2026Bomin Wang, Hangqi Zhou, Yibo Gao +1Interactive Medical Image Segmentation Stability-Plasticity Dilemma
School of Data Science, Fudan University, Shanghai, China.
MPCS: Neuroplastic Continual Learning via Multi-Component Plasticity and Topology-Aware EWC
May 4, 2026Joern HentschStability-Plasticity Dilemma Dynamic Neural Networks
NORACL: Neurogenesis for Oracle-free Resource-Adaptive Continual Learning
Apr 29, 2026Karthik Charan Raghunathan, Christian Metzner, Laura Kriener +1Stability-Plasticity Dilemma Dynamic Neural Networks
Institute of Neuroinformatics University of Zurich & ETH Zurich Zurich, Switzerland
Mitigating the Stability-Plasticity Dilemma in Adaptive Train Scheduling with Curriculum-Driven Continual DQN Expansion
Aug 19, 2024Achref Jaziri, Etienne Künzel, Visvanathan RameshStability-Plasticity Dilemma Non-Stationary RL
Department of Computer Science and Mathematics, Goethe University · HessianAI, Frankfurt am Main, Germany

Oct 1, 2026, cs.NEJ/K move · Enter open · S save

Continual Reinforcement Learning with Neuroevolution

Eleni Nisioti, Andrea Cossu, Kathrin Korte, Sebastian Risi

IT University of Copenhagen · University of Pisa · Sakana AI

Stability-Plasticity Dilemma Loss of Plasticity Evolution Strategies Continual RL Genetic Algorithms Neuroevolution

Open paper AskPDF arXiv

Despite many studies about causes and remedies of plasticity loss in Reinforcement Learning (RL) under continual task changes, no RL method has yet consistently achieved a good balance between adaptation and forgetting. Here we turn to an alternative optimization paradigm, neuroevolution (NE): algorithms that search directly in weight space through mutation and selection over a population of neural networks. Across a wide array of environments and environmental changes, with policies ranging from a few hundred parameters to million-parameter networks, we compare evolution strategies (ES) and genetic algorithms (GAs) against state-of-the-art continual RL variants and population-based RL. ES most consistently achieves a good stability-plasticity trade-off, while the GA is the most plastic method but forgets more than ES. To explain this, we study the return landscape around each method's solutions. ES finds the widest neighborhoods, i.e.\ regions of weight space in which perturbed policies still solve the task, and the size of the overlap between the neighborhoods of consecutive tasks correlates with a method's stability-plasticity trade-off. Rewarding behavioral diversity in a GA through novelty search makes the population even more plastic, at the cost of forgetting. Finally, symptoms of plasticity loss commonly reported in RL do not transfer to NE. Overall, these results establish NE as a competitive alternative to RL under continual task changes, and suggest that training under perturbations in weight space may be a useful mechanism for continual learning more broadly.

Momentum

Related topics

Latest papers 12