AI Paper Atlas

Research map / Reinforcement learning / Policy gradient and actor-critic

Error Amplification Limits ANN-to-SNN Conversion in Continuous Control

Zijie Xu, Zihan Huang, Yiting Dong, Kang Chen, Wenxuan Liu, Zhaofei Yu

ICML 2026 · Reinforcement learning › Policy gradient and actor-critic · approach: Regularized scalable deep value learning · 0 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
add CRPI to IF conversion (T=16)converted DDPG · MuJoCoaverage performance ratio: 82.57% -> 95.41%Improved
add CRPI to IF conversion (T=8)converted TD3 · MuJoCoaverage performance ratio: 64.71% -> 72.26%Improved
add CRPI to IF conversion (T=32)converted SAC · MuJoCoaverage performance ratio: 97.98% -> 99.70%Improved
add CRPI to MT neurons (T=4)converted TD3 · MuJoCoaverage performance ratio: 97.93% -> 98.09%No clear effect
add CRPI to IF neurons (T=32)DrQ-v2 SNN · DMC visualaverage performance ratio: 40.77% -> 74.19%Improved
add CRPI to IF neurons (T=64)DrQ-v2 SNN · DMC visualaverage performance ratio: 69.60% -> 91.84%Improved
add CRPI to SNM (T=8)DrQ-v2 SNN · DMC visualaverage performance ratio: 88.72% -> 96.27%Improved
add CRPI to MT (T=2)DrQ-v2 SNN · DMC visualaverage performance ratio: 94.85% -> 101.30%Improved
increase alpha in CRPI (ablation)CRPI · MuJoCo TD3 IF T=16cross-step error correlationImproved
replace ANN policy states with SNN-induced trajectory (ablation)TD3 ANN policy (IF T=8) · Ant-v4 reward decompositionreturn: 6505.26 -> 4051.77Hurt
replace ANN policy with SNN policy on ANN trajectory (ablation)TD3 (IF T=8) · Ant-v4 reward decompositionreturn: 6505.26 -> 6216.71No clear effect
use CRPI-converted SNN instead of directly trained Spiking-WMSNN on visual control · DMC visualaverage performance ratio: 68.54% -> 74.19%Improved

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