AI Paper Atlas

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

WIMLE: Uncertainty‑Aware World Models with IMLE for Sample‑Efficient Continuous Control

Mehran Aghabozorgi, Alireza Moazeni, Yanshu Zhang, Ke Li

ICLR 2026 · Reinforcement learning › Policy gradient and actor-critic · approach: Model-based RL with guarantees · 2 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 uncertainty-aware per-transition weighting (vs fixed w=1.0) (ablation)WIMLE · Humanoid-run (DMC)return curveImproved
add the learned world model (vs model-free variant) (ablation)WIMLE · Humanoid-run (DMC)return curveImproved
increase rollout horizon from H=1 to 4 to 6 (ablation)WIMLE · Humanoid-run (DMC)return curveImproved
increase rollout horizon from H=6 to H=8 (ablation)WIMLE · Humanoid-run (DMC)return curveNo clear effect
extend rollout horizon up to H=40 without scheduling (ablation)WIMLE · h1-hurdle-v0 (HumanoidBench)return curveNo clear effect
replace unimodal Gaussian world model with IMLE world model (ablation)WIMLE · Humanoid-run (DMC)return curveImproved
IMLE vs Gaussian weights evolve with training (ablation)WIMLE · Humanoid-run (DMC)weight dynamicsImproved
WIMLE vs BROWIMLE · DMC (16 tasks) @ 1MIQM normalized return: 0.846 -> 0.871Improved
WIMLE vs BROWIMLE · Dog & Humanoid (DMC) @ 1MIQM normalized return: 0.864 -> 0.897Improved
WIMLE vs SimBAV2WIMLE · HumanoidBench (14 tasks) @ 1MIQM success-normalized score: 0.799 -> 0.898Improved
WIMLE vs SimBAV2WIMLE · MyoSuite (10 tasks) @ 1MIQM success rate: 0.990 -> 0.980Hurt
WIMLE vs SimBAV2 at early trainingWIMLE · MyoSuite (10 tasks) @ 100kIQM success rate: 0.724 -> 0.460Hurt

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