Online Reinforcement Learning on Antmaze large-diverse
93.5ScoreRLPD
Evaluation Results
| Method | Links | |
|---|---|---|
| RLPDReward Setting=with true reward, Environment Steps=500k2023.10 | 93.5 | |
| UBEREnvironment Steps=500k2023.10 | 88.7 | |
| UBEREnvironment Steps=100k2023.10 | 82.7 | |
| RLPDReward Setting=with true reward, Environment Steps=100k2023.10 | 61.4 | |
| RLPDReward Setting=without true reward, Environment Steps=500k2023.10 | 0 | |
| BC-PEXEnvironment Steps=500k2023.10 | 0 | |
| RLPDReward Setting=without true reward, Environment Steps=100k2023.10 | 0 | |
| BC-PEXEnvironment Steps=100k2023.10 | 0 |