AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Learning From the Past with Cascading Eligibility Traces

Tokiniaina Raharison Ralambomihanta, Ivan Anokhin, Roman Pogodin, Samira Ebrahimi Kahou, Jonathan Cornford, Blake Aaron Richards

ICLR 2026 · Architectures and efficiency › RNNs and normalization · approach: Brain-inspired recurrent architectures

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
increase number of CET states (vs single-state standard ET) (ablation)CET with delayed error signal · MNIST (behavioral delays, 3-layer MLP)accuracyImproved
increase number of CET states (vs single-state standard ET) (ablation)CET with delayed error signal · CIFAR-10 (behavioral delays, small CNN)accuracyImproved
increase number of CET states (ablation)Actor-Critic actor with CET · CartPole and LunarLander (behavioral delays)mean episodic returnImproved
increase number of CET states (ablation)Actor-Critic actor with CET · MinAtar/SpaceInvaders (behavioral delays)mean episodic returnMixed
increase number of CET states (ablation)CET gradient approximation · CIFAR-10 (delays 1, 2, 4 s)cosine similarity to true gradientImproved
increase delay with higher-order CETs (ablation)CET gradient approximation · CIFAR-10 (long delay)cosine similarity to true gradientHurt
increase CET order with stacked retrograde delays (minutes) (ablation)MLP on MNIST and CNN on CIFAR-10 · retrograde delays, stacked across layerstest accuracyImproved
increase CET order with stacked retrograde delays (ablation)MLP on MNIST and CNN on CIFAR-10 · retrograde delays, stacked across layerstraining speedImproved
increase CET order with retrograde delays (ablation)CET gradient approximation · MNIST and CIFAR-10, retrogradecosine similarity to true gradientMixed
increase CET states with retrograde delays (ablation)Actor-Critic actor with CET · CartPole and LunarLander (retrograde)episodic returnImproved
increase network depth under stacked retrograde delaysCETs · retrograde delaysgradient estimate and learningHurt
apply CET at retrograde timescale on SpaceInvadersCET · MinAtar/SpaceInvaders (8 s and 120 s delay)episodic returnHurt

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