paper-with-me

Meta-Learning 벤치마크

Meta-Learning on ML10

6개 결과 · ⬇ CSV · JSON

Meta-test success rate

0 9 18 27 36 2019-10 2026-09 MAML — 36.0 (2019-10-24) RL^2 — 10.0 (2019-10-24) PEARL — 0.0 (2019-10-24) DnC — 5.4 (2020-02-08) MAML — 36.0 (2019-10-24)
RankModel Meta-test success rateMeta-train success rateMeta-test success rate (zero-shot) PaperCodeYear
1 MAML 36%25% Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning rlworkgroup/metaworld · farama-foundation/metaworld · avivne/bilinear-transduction · +6 2019
2 RL^2 10%50% Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning rlworkgroup/metaworld · farama-foundation/metaworld · avivne/bilinear-transduction · +6 2019
3 DnC 5.4% Analyzing Policy Distillation on Multi-Task Learning and Meta-Reinforcement Learning in Meta-World 2020
4 PEARL 0%42.78% Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning rlworkgroup/metaworld · farama-foundation/metaworld · avivne/bilinear-transduction · +6 2019
5 MZ+Recon 97.8%25 Procedural Generalization by Planning with Self-Supervised World Models 2021
6 MZ 97.6%26.5 Procedural Generalization by Planning with Self-Supervised World Models 2021
1–6 / 6 페이지당 10 20 50 100