AI Paper Atlas

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

Sample-Efficient Reinforcement Learning via Conservative Model-Based Actor-Critic

Zhihai Wang, Jie Wang, Qi Zhou, Bin Li, Houqiang Li

AAAI 2022 · Reinforcement learning › Policy gradient and actor-critic · approach: Off-policy actor-critic with expressive policies · 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 CMBAC instead of MBPOmodel-based control · Humanoidsample efficiency: 200 thousand steps matches that of MBPO at 300 thousand stepsImproved
use CMBAC instead of MBPOmodel-based control · Walker2d-NT and Hopper-NTaverage returnImproved
use CMBAC instead of MBPO and MOPO-Onlinemodel-based control with Gaussian action noise · Walker2d and HalfCheetah noisy environmentssample efficiency: 100k steps for HalfCheetah and 200k steps for Walker2dImproved
increase Q-network size (ablation)MBPO · Ant and Walker2daverage returnNo clear effect
learn multiple Q-value estimates from ensemble models (ablation)B-MBPO · Ant and Walker2daverage returnImproved
add conservative policy optimization using the bottom-k Q-value estimates (ablation)B-LMEQ-MBPO · Antaverage returnImproved
add conservative policy optimization using the bottom-k Q-value estimates (ablation)B-LMEQ-MBPO · Walker2daverage returnHurt
increase Q-network size (ablation)MBPO · Hopperaverage returnNo clear effect
learn multiple Q-value estimates from ensemble models (ablation)B-MBPO · Hopperaverage returnImproved
add conservative policy optimization using the bottom-k Q-value estimates (ablation)B-LMEQ-MBPO · Hopperaverage returnImproved
add conservative policy optimization using the bottom-k Q-value estimates (ablation)B-LMEQ-MBPO · HalfCheetahasymptotic performanceHurt
set the number of probabilistic networks per model to M=2 (ablation)CMBAC · Ant and Walker2daverage returnImproved

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