Offline Goal-Conditioned Reinforcement Learning on FetchReach (offline)
30.1Discounted ReturnAM
Evaluation results
| Method | Links | |
|---|---|---|
| AMLearning Paradigm=Actor-Critic, HER rate=0.52022.06 | 30.1 | |
| AMAlgorithm Category=Actor-Critic, config_value=0.52022.06 | 30.1 | |
| DDPGLearning Paradigm=Actor-Critic, HER rate=0.22022.06 | 29.8 | |
| DDPGAlgorithm Category=Actor-Critic, config_value=0.22022.06 | 29.8 | |
| GoFAR2022.06 | 28.2 | |
| GoFARAlgorithm Category=Supervised Learning2022.06 | 28.2 | |
| WGCSLLearning Paradigm=Supervised Learning, HER rate=1.02022.06 | 21.9 | |
| WGCSLAlgorithm Category=Supervised Learning, config_value=1.02022.06 | 21.9 | |
| GCSLLearning Paradigm=Supervised Learning, HER rate=1.02022.06 | 20.91 | |
| GCSLAlgorithm Category=Supervised Learning, config_value=1.02022.06 | 20.91 |