AI Paper Atlas

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

Implicit Action Chunking for Smooth Continuous Control

Bosun Liang, Shuo Pei, Zirui Chen, Chuanzhi Fan, Chen Sun, Yuankai Wu, Huachun Tan, Yong Wang

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
add execution window to HG-TD3 (ablation)HG-TD3 · CARLA LCOsuccess rate: 0.00 -> 0.50Improved
add value window to HG-TD3 (ablation)HG-TD3 · CARLA LCOsuccess rate: 0.00 -> 0.65Improved
add smoothness regularizer to HG-TD3 (ablation)HG-TD3 · CARLA LCOsuccess rate: 0.00 -> 0.60Improved
add regularizer to value window (ablation)Value Window · CARLA LCOsuccess rate: 0.65 -> 0.80Improved
add execution window to value window plus regularizer (ablation)Value Window + Reg · CARLA LCOsuccess rate: 0.80 -> 1.00Improved
add execution window to value window plus regularizer (ablation)Value Window + Reg · CARLA LCOAbsAccP95: 1.381 -> 1.195Improved
use zero-order hold instead of dissipative decay (ablation)DWS · CARLA AEBreward: 388.66 -> 390.70Improved
use zero-order hold instead of dissipative decay (ablation)DWS · CARLA AEBJerkRMS_a: 49.24 -> 47.90Improved
increase window size h from 1 to 3 (ablation)DWS · EMSreward: -2179 -> -1393Improved
increase window size h from 3 to 5 (ablation)DWS · EMSreward: -1393 -> -2387Hurt
add smoothness regularization lambda_S=0.10 vs none (ablation)DWS · EMSreward: -2355 -> -1393Improved
raise lambda_S from 0.10 to 0.40 (ablation)DWS · EMSreward: -1393 -> -2849Hurt

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