AI Paper Atlas

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

Flow Matching Policy Gradients

David McAllister, Songwei Ge, Brent Yi, Chung Min Kim, Ethan Weber, Hongsuk Choi, Haiwen Feng, Angjoo Kanazawa

ICLR 2026 · Reinforcement learning › Policy gradient and actor-critic · approach: Model-based RL with guarantees

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
replace Gaussian PPO with FPO flow policyMuJoCo Playground policies · MuJoCo Playground (10 tasks)average evaluation reward: 667.8 -> 759.3Improved
use FPO ratio instead of denoising-MDP DPPO for diffusion policydiffusion policy · MuJoCo Playground (10 tasks)average evaluation reward: 652.5 -> 759.3Improved
increase number of (tau, eps) samples from 1 to 8 (ablation)FPO · MuJoCo Playground (10 tasks)average evaluation reward: 691.6 -> 759.3Improved
use 4 instead of 8 (tau, eps) pairs (ablation)FPO · MuJoCo Playground (10 tasks)average evaluation reward: 759.3 -> 731.2Hurt
use epsilon-MSE instead of velocity (u-MSE) flow matching loss (ablation)FPO · MuJoCo Playground (10 tasks)average evaluation reward: 664.6 -> 759.3Improved
raise clipping epsilon from 0.05 to 0.2 (ablation)FPO · MuJoCo Playground (10 tasks)average evaluation reward: 759.3 -> 526.4Hurt
raise clipping epsilon from 0.05 to 0.1 (ablation)FPO · MuJoCo Playground (10 tasks)average evaluation reward: 759.3 -> 623.3Hurt
tune Gaussian PPO hyperparameters (lr 3e-4, clip 0.1) versus Playground default (ablation)Gaussian PPO · MuJoCo Playground (10 tasks)average evaluation reward: 577.2 -> 667.8Improved
use FPO instead of Gaussian PPO with root+hands goal conditioninghumanoid tracking policy · Humanoid tracking, root + hands goalssuccess rate: 46.5% -> 70.6%Improved
use FPO instead of Gaussian PPO with root-only goal conditioninghumanoid tracking policy · Humanoid tracking, root goalssuccess rate: 29.8% -> 54.3%Improved
use FPO instead of Gaussian PPO with full all-joint conditioninghumanoid tracking policy · Humanoid tracking, all-joint goalssuccess rate: 98.7% -> 96.4%Hurt
use FPO instead of Gaussian PPO with all-joint conditioninghumanoid tracking policy · Humanoid tracking, all-joint goalsMPJPE: 31.62 -> 41.98Hurt

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