AI Paper Atlas

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

Real-time 'Actor-Critic' Tracking

Boyu Chen, Dong Wang, Peixia Li, Shuang Wang, Huchuan Lu

ECCV 2018 · Reinforcement learning › Policy gradient and actor-critic · approach: Actor-critic theory · 141 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 reinforcement learning (Critic-guided DDPG) offline training (ablation)ACT · OTB-2013precision (20px): 0.876 -> 0.905Improved
add reinforcement learning (Critic-guided DDPG) offline training (ablation)ACT · OTB-2013success AUC: 0.639 -> 0.657Improved
use expert decision guidance instead of normal DDPG exploration (ablation)ACT · OTB-2013precision (20px): 0.861 -> 0.905Improved
use expert decision guidance instead of normal DDPG exploration (ablation)ACT · OTB-2013success AUC: 0.616 -> 0.657Improved
add first-frame supervised initialization of Actor during offline training (ablation)ACT · OTB-2013precision (20px): 0.849 -> 0.905Improved
add first-frame supervised initialization of Actor during offline training (ablation)ACT · OTB-2013success AUC: 0.577 -> 0.657Improved
add offline pretraining of Actor rather than plain VGG-M init (ablation)ACT · OTB-2013precision (20px): 0.787 -> 0.905Improved
add offline pretraining of Actor rather than plain VGG-M init (ablation)ACT · OTB-2013success AUC: 0.550 -> 0.657Improved
use one continuous action (ACT) instead of iterative discrete actions (ADNet)ACT · OTB-2013FPS: 3 -> 30Improved
use one continuous action (ACT) instead of iterative discrete actions (ADNet)ACT · OTB-2015precision (20px): 0.880 -> 0.859Hurt
use ACT instead of MDNet random sampling searchACT · OTB-2013precision (20px): 0.948 -> 0.905Hurt

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