Meta Learning On Mt50
평가 지표
Average Success Rate
평가 결과
이 벤치마크에서 각 모델의 성능 결과
모델 이름 | Average Success Rate | Paper Title | Repository |
|---|---|---|---|
| NDP | 11% | Neural Dynamic Policies for End-to-End Sensorimotor Learning | - |
| Multi-task multi-head SAC | 35.85% | Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning | |
| SoftModule | 60.0% | Multi-Task Reinforcement Learning with Soft Modularization | |
| DisCor | 26% | DisCor: Corrective Feedback in Reinforcement Learning via Distribution Correction |
0 of 4 row(s) selected.