AI Paper Atlas

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

Trust-Region Diffusion Policies for Massively Parallel On-Policy RL

Huy Le, Onur Celik, Denis Blessing, Tai Hoang, Claas A Voelcker, Axel Brunnbauer, Felix Richter, Michael Volpp, Gerhard Neumann

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
use a single diffusion step (T=1) instead of 8 (ablation)TruDi · MuJoCo Playground Humanoidaggregated returnHurt
increase diffusion steps from 8 to 32 (ablation)TruDi · MuJoCo Playground Humanoidaggregated returnNo clear effect
set trust-region epsilon too large (50) versus 0.1 to 0.4 (ablation)TruDi · IsaacLabnormalized returnHurt
use a very small trust-region epsilon (0.01) (ablation)TruDi · IsaacLabnormalized returnHurt
evaluate with probability-flow ODE (c=1.0) instead of SDE sampling (ablation)TruDi · MuJoCo Playground Humanoidaggregated returnImproved
evaluate with ODE instead of Best-of-K (K=10, 20) selection (ablation)TruDi · MuJoCo Playground Humanoidaggregated returnImproved
extend REPPO training from 50M to 150M stepsREPPO · MuJoCo Playground Humanoidepisode returnNo clear effect
use diffusion policy TruDi instead of Gaussian REPPOREPPO · StackCube (multimodality)behavior entropy: 0 -> 0.87Improved
use diffusion policy TruDi instead of Gaussian REPPOREPPO · MuJoCo Playground Humanoid (50M steps)episode return (IQM): 29.6 -> 34.8Improved
use TruDi instead of DIMEDIME · MuJoCo Playground Humanoid (50M steps)episode return (IQM): 15.6 -> 34.8Improved
use TruDi instead of DIME on PushTDIME · PushT (multimodality)episode return: 171.92 -> 167.32Hurt

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