Reinforcement Learning on Ant-ET
4,788.6Average ReturnDiff-SR
Evaluation results
| Method | Links | |
|---|---|---|
| Diff-SRRL Category=Representation RL2024.06 | 4,788.6 | |
| LV-RepRL Category=Representation RL2024.06 | 2,511.8 | |
| SACRL Category=Model-Free RL2024.06 | 2,012.7 | |
| SPEDERL Category=Representation RL2024.06 | 806.2 | |
| DeepSFRL Category=Representation RL2024.06 | 768.1 | |
| PolyGRADRL Category=Model-Based RL2024.06 | 433.6 | |
| Best MBBLRL Category=Model-Based RL2024.06 | 275.4 | |
| PETS-RSRL Category=Model-Based RL2024.06 | 130 | |
| TRPORL Category=Model-Free RL2024.06 | 116.8 | |
| PETS-CEMRL Category=Model-Based RL2024.06 | 81.6 | |
| PPORL Category=Model-Free RL2024.06 | 80.1 | |
| ME-TRPORL Category=Model-Based RL2024.06 | 42.6 |