AI Paper Atlas

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

ACE: An Actor Ensemble Algorithm for Continuous Control with Tree Search

Shangtong Zhang, Hengshuai Yao

AAAI 2019 · Reinforcement learning › Policy gradient and actor-critic · approach: Actor-critic theory · 20 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
use multiple independently initialized actors and select the proposal with the highest critic value instead of using a single actor (ablation)DDPG · Roboschool tasksnumber of games outperforming DDPG: 6 games (lost in 3 games and tied in 3 games)Improved
add look-ahead tree search with a learned value prediction model (ablation)Ensemble-DDPG · Roboschool tasksnumber of games outperforming Ensemble-DDPG: 9 gamesImproved
replace the value prediction model with a learned transition model (ablation)ACE · Roboschool tasksnumber of games outperforming Ensemble-DDPG: 2 games (lost in 3 games and tied in 7 games)Hurt
increase network width while keeping depth comparable (ablation)DDPG · Roboschool tasksnumber of games outperforming DDPG: 1 gameNo clear effect
share a bottom representation layer between actor and critic (ablation)DDPG · Roboschool tasksnumber of games outperforming DDPG: 2 games (lost in 2 games and tied in 8 games)No clear effect
update only the selected actor at each time step rather than updating all actors (ablation)ACE · Roboschool tasksoverall performance: ACE was slightly better overall; ACE-Alt had lower varianceMixed
use a medium ensemble size (N=5) rather than the tested alternatives (ablation)ACE · HalfCheetahmean episode returnImproved
use a medium planning depth (d=1) rather than the tested alternatives (ablation)ACE · HalfCheetahmean episode returnImproved
increase the ensemble size from N=5 to N=10 at d=1 (ablation)ACE · HalfCheetahenvironment steps per second: 27.82 -> 16.12Hurt
increase planning depth from d=1 to d=2 at N=5 (ablation)ACE · HalfCheetahenvironment steps per second: 27.82 -> 6.34Hurt

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