MZ

Reported on 3 benchmarks across 1 task · 1 paper · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Methodology3 results

Meta-LearningonML45
Meta-train success rate· 2021-11-02
77.2
SOTA
Procedural Generalization by Planning with Self-Supervised World Models arXiv:2111.01587
Meta-LearningonML10
Meta-test success rate (zero-shot)· 2021-11-02
26.5
SOTA
Procedural Generalization by Planning with Self-Supervised World Models arXiv:2111.01587
Meta-LearningonML45
Meta-test success rate (zero-shot)· 2021-11-02
17.7
best: 18.5 (MZ+Recon)
Procedural Generalization by Planning with Self-Supervised World Models arXiv:2111.01587