AI Paper Atlas

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

How Does the Lagrangian Guide Safe Reinforcement Learning through Diffusion Models?

Xiaoyuan Cheng, Wenxuan Yuan, Boyang Li, Yuanchao Xu, Yiming Yang, Hao Liang, Bei Peng, Robert Loftin, Zhuo Sun, Yukun Hu

ICML 2026 · Reinforcement learning › Policy gradient and actor-critic · approach: Safe policy improvement · 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
increase Monte Carlo sample size N from 2 to 16 (ablation)ALGD · PointPush1GPU time (ms): 5.3 -> 5.9No clear effect
increase Monte Carlo sample size N from 2 to 16 (ablation)ALGD · PointButton2GPU time (ms): 4.6 -> 5.0No clear effect
increase Monte Carlo sample size N (ablation)ALGD · Safe RL taskstraining stability and returnImproved
use augmented Lagrangian instead of standard Lagrangian for diffusion guidance (ablation)Lagrangian-guided diffusion policy · Safe RL taskstraining stability and constraint violationImproved
add augmented Lagrangian to SAC with Gaussian policySAC · Safe RL tasksreward and costNo clear effect
use ALGD instead of on-policy PPO+LagPPO+Lag · Safe RL taskssample efficiencyImproved

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