AI Paper Atlas

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

When to Update Your Model: Constrained Model-based Reinforcement Learning

Tianying Ji, Yu Luo, Fuchun Sun, Mingxuan Jing, Fengxiang He, Wenbing Huang

NeurIPS 2022 · Reinforcement learning › Policy gradient and actor-critic · approach: Model-based RL with guarantees · 7 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 CMLO's event-triggered model updates instead of fixed model-training intervals (ablation)CMLO with SAC · HalfCheetahaverage returnImproved
Use CMLO's event-triggered model updates instead of fixed model-training intervals (ablation)CMLO with SAC · Antaverage returnImproved
Use a fixed model-training interval of 250 instead of the event-triggered mechanism (ablation)CMLO with SAC · HalfCheetah and Antaverage returnHurt
Use CMLO's event-triggered model updates instead of fixed model-training intervals (ablation)CMLO with TRPO · HalfCheetahaverage returnImproved
Use CMLO's event-triggered model updates instead of fixed model-training intervals (ablation)CMLO with TRPO · Antaverage returnImproved
Use event-triggered updates instead of the most-frequently triggered case (ablation)CMLO with iLQR · DKitty-Standasymptotic performanceNo clear effect
Use event-triggered updates instead of the most-frequently triggered case (ablation)CMLO with iLQR · DKitty-Standcomputation costImproved
Use event-triggered updates instead of the most-frequently triggered case (ablation)CMLO with iLQR · Panda-Reachingasymptotic performanceNo clear effect
Use event-triggered updates instead of the most-frequently triggered case (ablation)CMLO with iLQR · Panda-Reachingcomputation costImproved
Use CMLO's event-triggered model updates and constrained model-shift strategyCMLO with SAC · Six continuous-control tasks: HalfCheetah, Hopper, Walker2d, Swimmer, Ant, and Humanoidsample efficiencyImproved
Use CMLO's event-triggered model updates and constrained model-shift strategyCMLO with SAC · Six continuous-control tasks: HalfCheetah, Hopper, Walker2d, Swimmer, Ant, and Humanoidasymptotic performanceImproved
Use CMLO's event-triggered model updates and constrained model-shift strategyCMLO with SAC · Six continuous-control tasks: HalfCheetah, Hopper, Walker2d, Swimmer, Ant, and Humanoidasymptotic performanceNo 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