AI Paper Atlas

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

Model-based Policy Optimization with Unsupervised Model Adaptation

Jian Shen, Han Zhao, Weinan Zhang, Yong Yu

NeurIPS 2020 · Reinforcement learning › Policy gradient and actor-critic · approach: Model-based RL with guarantees · 6 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 unsupervised feature-distribution adaptation with Wasserstein-1 distance to MBPOMBPO / AMPO · Six MuJoCo continuous-control taskssample efficiencyImproved
Add unsupervised feature-distribution adaptation with Wasserstein-1 distance to MBPOMBPO / AMPO · Six MuJoCo continuous-control tasksasymptotic returnImproved
Add unsupervised model adaptationMBPO dynamics model · One-step model predictionmodel lossImproved
Add unsupervised model adaptationMBPO dynamics model · Hoppermulti-step compounding errorImproved
Use MMD rather than Wasserstein-1 distance for feature alignment (ablation)AMPO · Three continuous-control environmentsreturnImproved
Increase the number of model-adaptation updates (ablation)AMPO · HopperreturnMixed
Use longer rollout lengths earlier in training (ablation)AMPO and MBPO · HopperreturnMixed
Increase the number of policy updates per environment step (ablation)AMPO and MBPO · Continuous-control environmentsreturnMixed
Continue model adaptation throughout training instead of early stopping (ablation)AMPO · Hopper and other continuous-control environmentsreturnNo clear effect
Share feature-extractor weights across real and simulated data (ablation)AMPO · Continuous-control environmentsreturnNo clear effect
Fix the real-data feature extractor rather than learning separate real and simulated extractors (ablation)AMPO · Continuous-control environmentsreturnNo 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