AI Paper Atlas

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

Transfer Value Iteration Networks

Junyi Shen, Hankz Hankui Zhuo, Jin Xu, Bin Zhong, Sinno Pan

AAAI 2020 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Statistical alignment and hypothesis testing · 4 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
Transfer reward and transition knowledge from NEWS-15, mapping target features and adapting shared actionsVIN policy for Moore · Moore-15, 1k target data%Opt: 77.3 -> 90.1Improved
Use TVIN instead of heuristic transferred initializationVIN_i on Moore · Moore-15, 1k target data%Opt: 88.6 -> 90.1Improved
Transfer policy knowledge from NEWS-15VIN policy for Moore · Moore-28, 10k target data%Suc: 68.0 -> 91.8Improved
Set iteration count K = 20 rather than K = 10 (ablation)TVIN · Moore-15, NEWS-9 source%Opt: 78.0 -> 81.6Improved
Set iteration count K = 30 rather than K = 20 (ablation)TVIN · Moore-15, NEWS-9 source%Opt: 81.6 -> 80.1Hurt
Set kernel size F = 5 rather than F = 3 (ablation)TVIN · Moore-15, NEWS-9 source%Opt: 80.1 -> 88.3Improved
Set kernel size F = 7 rather than F = 5 (ablation)TVIN · Moore-15, NEWS-9 source%Opt: 88.3 -> 85.3Hurt
Transfer more common actions (ablation)TVIN · Moore-15, 1k data; NEWS-9 source%Opt: 82.0 -> 88.3Improved
Transfer policy knowledge from NEWS-9 rather than train VIN from scratchVIN policy for Moore · Moore-15, 1k target data%Suc: 81.7 -> 91.0Improved

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