Online Reinforcement Learning on Antmaze large-play
94.8ScoreRLPD
Evaluation Results
| Method | Links | |
|---|---|---|
| RLPDReward Setting=with true reward, Environment Steps=500k2023.10 | 94.8 | |
| UBEREnvironment Steps=500k2023.10 | 83.3 | |
| UBEREnvironment Steps=100k2023.10 | 62.8 | |
| RLPDReward Setting=with true reward, Environment Steps=100k2023.10 | 62.1 | |
| 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 |