AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Meta-Learning through Hebbian Plasticity in Random Networks

Elias Najarro, Sebastian Risi

NeurIPS 2020 · Reinforcement learning › Visual and representation RL · approach: Curriculum and environment design · 22 citations (OpenAlex)

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 static weights with evolved Hebbian plasticity rules from random initial weightsCNN+MLP policy · CarRacing-v0average reward: 711±16 -> 872±11Improved
Replace static weights with evolved Hebbian plasticity rulesAnt quadruped · Unseen left-front-leg damagedistance travelled: 68 ± 56 -> 452 ± 95Improved
Replace static weights with evolved Hebbian plasticity rulesAnt quadruped · Undamaged morphology (seen)distance travelled: 1604 ± 171 -> 1051 ± 113Hurt
Replace static weights with evolved Hebbian plasticity rulesAnt quadruped · Right front leg damage (seen)distance travelled: 1431 ± 54 -> 1019 ± 116Hurt
Use random instead of evolved Hebbian coefficients (ablation)Hebbian network · Weight dynamics (PCA)weight trajectory structureHurt
Sample initial weights from N(0, 0.1) instead of U[-0.1, 0.1] (ablation)Hebbian quadruped · Ant quadrupedperformanceNo clear effect

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