AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Wavelet Policy: Lifting Scheme for Policy Learning in Long-Horizon Tasks

Hao Huang, Shuaihang Yuan, Geeta Chandra Raju Bethala, Congcong Wen, Anthony Tzes, Yi Fang

ICCV 2025 · Reinforcement learning › Visual and representation RL · approach: Skill learning and diffusion policies · 1 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
use causal convolution instead of non-causal convolution (ablation)Wavelet Policy · Franka Kitchensuccess T1: 0.494 -> 0.953Improved
use causal convolution instead of non-causal convolution (ablation)Wavelet Policy · Franka Kitchensuccess T4: 0.033 -> 0.339Improved
use causal convolution instead of non-causal convolution (ablation)Wavelet Policy · Franka Kitchensuccess T5: 0.002 -> 0.041Improved
use learnable lifting networks instead of fixed Haar wavelet (ablation)Wavelet Policy · Franka Kitchensuccess T1: 0.884 -> 0.953Improved
use learnable lifting networks instead of fixed Haar wavelet (ablation)Wavelet Policy · Franka Kitchensuccess T4: 0.265 -> 0.339Improved
use learnable lifting networks instead of fixed DB2 wavelet (ablation)Wavelet Policy · Franka Kitchensuccess T4: 0.225 -> 0.339Improved
use learnable lifting networks instead of fixed DB2 wavelet (ablation)Wavelet Policy · Franka Kitchensuccess T5: 0.029 -> 0.041Improved
replace MinGPT in BeT with wavelet networkBeT · CARLA self-drivingsuccess rate: 0.832 -> 0.847Improved
replace MinGPT in BeT with wavelet networkBeT · Franka Kitchensuccess T4: 0.275 -> 0.339Improved
replace MinGPT in BeT with wavelet networkBeT · Franka Kitchensuccess T2: 0.773 -> 0.775No clear effect
replace Transformer decoders in Diffusion Policy with wavelet networkDiffusion Policy · Robomimic Transport-mhsuccess rate: 0.440 -> 0.497Improved
replace Transformer decoders in Diffusion Policy with wavelet networkDiffusion Policy · Push-Tsuccess rate: 0.942 -> 0.958Improved

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