AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Hierarchical Policy Learning via Spectral Decomposition

Shuxin Cao, Liquan Wang, Walker Byrnes, Yiye Chen, Yilun Du, Animesh Garg

ICML 2026 · Reinforcement learning › Visual and representation RL · approach: Skill learning and diffusion policies · 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 language to the low-frequency predictor (ablation)CSP · LIBERO-90 K=16success rate (%): 22.2 -> 91.6Improved
add language to the low-frequency predictor (ablation)CSP · LIBERO-10 K=16success rate (%): 64.5 -> 81.0Improved
add low-frequency conditioning to the high-frequency predictor (ablation)CSP · LIBERO-10 K=32success rate (%): 51.5 -> 75.0Improved
predict low frequency before high frequency (not reversed) (ablation)CSP · LIBERO-90 K=16success rate (%): 49.6 -> 91.6Improved
predict low frequency before high frequency (not reversed) (ablation)CSP · LIBERO-10 K=16success rate (%): 35.5 -> 81.0Improved
add hierarchical coarse-to-fine conditioning to spectral diffusion (ablation)Frequency Diffusion · LIBERO-90 Set A large noisesuccess rate (%): 73.0 -> 87.5Improved
add causal frequency modeling over no-hierarchy (ablation)No Hierarchy · LIBERO-90 Set B large noisesuccess rate (%): 72.5 -> 80.0Improved
add hierarchy on Stack under teleoperation noise (ablation)Frequency Diffusion · Stack (noise)success rate (%): 81.3 -> 75.0Hurt
add hierarchy with no noise on Set B (ablation)No Hierarchy · LIBERO-90 Set B no noisesuccess rate (%): 96.0 -> 94.0No clear effect
vary low-frequency cutoff 20%-40% (ablation)CSP · LIBERO / MimicGensuccess rate (%)No clear effect
use CSP over Action Binning at chunk size 64Action Binning · MimicGen mean (chunk size 64)success rate (%): 31.8 -> 50.0Improved
use CSP over ACT at longer chunk size 64ACT · MimicGen mean (chunk size 64)success rate (%): 9.0 -> 50.0Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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