AI Paper Atlas

Research map / Continual learning / Online and replay-based

Neuro-evolutionary Continual Reinforcement Learning

Pengyi Li, Hongyao Tang, Yifu Yuan, YAN ZHENG, Xin Xu, Jianye HAO

ICML 2026 · Continual learning › Online and replay-based · approach: Plasticity-preserving continual reinforcement learning

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace semantic-similarity mask construction with random mask construction (ablation)Nevo-CRL · CW10average performanceHurt
add population of masks and policies versus single mask and single RL individual (ablation)Nevo-CRL · CW10average performanceImproved
replace random crossover with importance-guided crossover (ablation)Nevo-CRL · CW10average performanceImproved
add pruning of low-activity connections (ablation)Nevo-CRL · CW10average performanceNo clear effect
add pruning of low-activity connections (ablation)Nevo-CRL · CW10capacity utilization: 100% after a few tasks without pruningImproved
use Nevo-CRL instead of CoTASPCoTASP · CW10average performance P: 0.89 -> 0.96Improved
use Nevo-CRL instead of CoTASPCoTASP · CW20average performance P: 0.86 -> 0.93Improved
use Nevo-CRL instead of PackNetPackNet · CW10generalization G: 0.38 -> 0.41Hurt
use Nevo-CRL instead of CoTASPCoTASP · CW10generalization G: 0.47 -> 0.41Improved
use Nevo-CRL instead of CoTASP on Brax HalfCheetah transferCoTASP · Brax HalfCheetah transferaverage return: 780.71 -> 3211.93Improved
use Nevo-CRL instead of CoTASP on Brax Ant forgettingCoTASP · Brax Ant forgettingaverage return: 2746 -> 4003Improved
use population-based training instead of single policy (computational cost)CoTASP · CW20training time: 45.9 -> 70.8 hoursHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy