AI Paper Atlas

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

Action Manifold Smoothing: A Lipschitz Pathway Perspective on High-Dimensional Reinforcement Learning

Zhihao Lin

ICML 2026 · Reinforcement learning › Policy gradient and actor-critic · approach: Regularized scalable deep value learning

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 Neighborhood TD and LayerNorm Q-network (AMS)SAC · Dog-Runepisodic return: 45 ± 95 -> 427 ± 25Improved
add Neighborhood TD and LayerNorm Q-network (AMS)TD3 · Dog-Runepisodic return: 92 ± 121 -> 387 ± 32Improved
add AMSSAC · Quadruped-Runepisodic return: 301 ± 8 -> 781 ± 61Improved
add AMSTD3 · Quadruped-Runepisodic return: 576 ± 212 -> 765 ± 32Improved
add Neighborhood TD to LayerNorm Q-network (ablation)AMS-TD3 · Quadruped-Runepisodic return: 730 ± 119 -> 765 ± 32Improved
add LayerNorm in Q-network to Neighborhood TD (ablation)AMS-TD3 · Quadruped-Runepisodic return: 732 ± 59 -> 765 ± 32Improved
add Neighborhood TD to LayerNorm Q-network (ablation)AMS-SAC · Quadruped-Runepisodic return: 714 ± 67 -> 781 ± 61Improved
add LayerNorm in Q-network to Neighborhood TD (ablation)AMS-SAC · Quadruped-Runepisodic return: 726 ± 41 -> 781 ± 61Improved
add AMSTD3 · H1-Walk and H1-Runepisodic return: 787 ± 57 vs 775 ± 121 (H1-Walk); 658 ± 190 vs 614 ± 278 (H1-Run)No clear effect
add AMSTD3 · Cheetah-Runepisodic return: 753 ± 27 vs 712 ± 27No clear effect
raise neighborhood radius from 0.2 to 0.4 (ablation)AMS-TD3 · Quadruped-Runepisodic return: 766 ± 26 -> 716 ± 64No clear effect
reduce neighbors from K=8 to K=6 (ablation)AMS-TD3 · Quadruped-Runepisodic return: 766 ± 26 -> 737 ± 20No clear effect

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