Offline Goal-Conditioned Reinforcement Learning on FetchSlide (offline)
2.73Discounted ReturnWGCSL
Evaluation Results
| Method | Links | |
|---|---|---|
| WGCSLLearning Paradigm=Supervised Learning, HER rate=1.02022.06 | 2.73 | |
| WGCSLAlgorithm Category=Supervised Learning, config_value=1.02022.06 | 2.73 | |
| GoFAR2022.06 | 2.47 | |
| GoFARAlgorithm Category=Supervised Learning2022.06 | 2.47 | |
| GCSLLearning Paradigm=Supervised Learning, HER rate=1.02022.06 | 1.75 | |
| GCSLAlgorithm Category=Supervised Learning, config_value=1.02022.06 | 1.75 | |
| AMLearning Paradigm=Actor-Critic, HER rate=0.52022.06 | 1.46 | |
| AMAlgorithm Category=Actor-Critic, config_value=0.52022.06 | 1.46 | |
| DDPGLearning Paradigm=Actor-Critic, HER rate=0.52022.06 | 1.08 | |
| DDPGAlgorithm Category=Actor-Critic, config_value=0.52022.06 | 1.08 |