Offline Goal-Conditioned Reinforcement Learning on HandReach (offline)
11.5Discounted ReturnGoFAR
Evaluation results
| Method | Links | |
|---|---|---|
| GoFAR2022.06 | 11.5 | |
| GoFARAlgorithm Category=Supervised Learning2022.06 | 11.5 | |
| WGCSLLearning Paradigm=Supervised Learning, HER rate=1.02022.06 | 5.97 | |
| WGCSLAlgorithm Category=Supervised Learning, config_value=1.02022.06 | 5.97 | |
| GCSLLearning Paradigm=Supervised Learning, HER rate=1.02022.06 | 1.37 | |
| GCSLAlgorithm Category=Supervised Learning, config_value=1.02022.06 | 1.37 | |
| DDPGLearning Paradigm=Actor-Critic, HER rate=0.52022.06 | 0.81 | |
| DDPGAlgorithm Category=Actor-Critic, config_value=0.52022.06 | 0.81 | |
| AMLearning Paradigm=Actor-Critic, HER rate=0.52022.06 | 0 | |
| AMAlgorithm Category=Actor-Critic, config_value=0.52022.06 | 0 |