AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Curriculum Reinforcement Learning using Optimal Transport via Gradual Domain Adaptation

Peide Huang, Mengdi Xu, Jiacheng Zhu, Laixi Shi, Fei Fang, Ding Zhao

NeurIPS 2022 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Statistical alignment and hypothesis testing · 3 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 smaller delta alpha (0.2, 0.1, 0.05) (ablation)GRADIENT · Mazetime-to-thresholdNo clear effect
use GRADIENT curriculum instead of baseline curriculaGRADIENT (PPO) · Mazetime-to-thresholdImproved
uniform domain randomization instead of no curriculumPPO learner · Mazelearning efficiencyImproved
uniform domain randomization instead of linear interpolation curriculumPPO learner · Mazelearning efficiencyImproved
use GRADIENT or SPDL (target-aware) instead of other baselinesSAC learner · PointMasstime-to-thresholdImproved
use GRADIENT instead of SPDLSAC learner · PointMasstime-to-thresholdImproved
use GRADIENT instead of SPDL on non-Gaussian targetSAC learner · FetchPushtime-to-threshold and asymptotic performanceImproved
use target-aware methods (SPDL, GRADIENT) instead of ALP-GMM and GoalGANSAC learner · FetchPushperformanceImproved
use domain randomization instead of ALP-GMM and GoalGANSAC learner · FetchPushasymptotic performanceImproved
use learned distance embedding with episodic-reward surrogate metric instead of l2 distance (ablation)GRADIENT · U-Mazeinterpolation qualityImproved

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