Meta Learning On Ml10
평가 지표
Meta-test success rate (zero-shot)
Meta-train success rate
평가 결과
이 벤치마크에서 각 모델의 성능 결과
모델 이름 | Meta-test success rate (zero-shot) | Meta-train success rate | Paper Title | Repository |
|---|---|---|---|---|
| MZ | 26.5 | 97.6% | Procedural Generalization by Planning with Self-Supervised World Models | - |
| RL^2 | - | 50% | Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning | |
| DnC | - | - | Analyzing Policy Distillation on Multi-Task Learning and Meta-Reinforcement Learning in Meta-World | - |
| PEARL | - | 42.78% | Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning | |
| MAML | - | 25% | Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning | |
| MZ+Recon | 25 | 97.8% | Procedural Generalization by Planning with Self-Supervised World Models | - |
0 of 6 row(s) selected.