Offline Goal-Conditioned Reinforcement Learning on FetchPick (offline)
19.7Discounted ReturnGoFAR
Evaluation results
| Method | Links | |
|---|---|---|
| GoFAR2022.06 | 19.7 | |
| GoFARAlgorithm Category=Supervised Learning2022.06 | 19.7 | |
| AMLearning Paradigm=Actor-Critic, HER rate=0.52022.06 | 18.4 | |
| AMAlgorithm Category=Actor-Critic, config_value=0.52022.06 | 18.4 | |
| DDPGLearning Paradigm=Actor-Critic, HER rate=0.52022.06 | 16.8 | |
| DDPGAlgorithm Category=Actor-Critic, config_value=0.52022.06 | 16.8 | |
| WGCSLLearning Paradigm=Supervised Learning, HER rate=1.02022.06 | 9.84 | |
| WGCSLAlgorithm Category=Supervised Learning, config_value=1.02022.06 | 9.84 | |
| GCSLLearning Paradigm=Supervised Learning, HER rate=1.02022.06 | 8.94 | |
| GCSLAlgorithm Category=Supervised Learning, config_value=1.02022.06 | 8.94 |