AI Paper Atlas

Research map / Time series / Long-term forecasting

Wavelet Predictive Representations for Non-Stationary Reinforcement Learning

Min Wang, Xin Li, Ye He, Yao-Hui Li, Hasnaa Bennis, Riashat Islam, Mingzhong Wang

ICLR 2026 · Time series › Long-term forecasting · approach: Attention for time series forecasting · 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 the wavelet representation (Y) network (ablation)WISDOM · Meta-Worldsuccess rate / convergenceImproved
add the auto-regressive loss to the Y network objective (ablation)WISDOM · Meta-Worldsuccess rate / convergenceImproved
add the wavelet TD loss to the Y network objective (ablation)WISDOM · Meta-Worldsuccess rate / convergenceImproved
use an MLP context encoder instead of an RNN encoder (ablation)WISDOM · Meta-Worldsuccess rate / convergenceImproved
apply DWT to each variate independently (variable-wise encoding) instead of concatenated features (ablation)WISDOM · Meta-Worldsuccess rate / convergenceHurt
add WISDOM wavelet task representations under higher non-stationarity degreeWISDOM vs baselines · Meta-World, MuJoCo, Type-1 Diabetesfinal performanceImproved
inject Gaussian noise N(0,1) into statesWISDOM and baselines · Meta-Worldsuccess rateMixed
swap SAC backbone for DDPG (ablation)WISDOM · Meta-WorldreturnHurt

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