Reinforcement Learning on Walker-ET
3,722.2Average ReturnDiff-SR
Evaluation results
| Method | Links | |
|---|---|---|
| Diff-SRRL Category=Representation RL2024.06 | 3,722.2 | |
| LV-RepRL Category=Representation RL2024.06 | 2,523.5 | |
| SACRL Category=Model-Free RL2024.06 | 2,216.4 | |
| SPEDERL Category=Representation RL2024.06 | 501.6 | |
| PETS-RSRL Category=Model-Based RL2024.06 | 312.5 | |
| Best MBBLRL Category=Model-Based RL2024.06 | 312.5 | |
| PPORL Category=Model-Free RL2024.06 | 306.1 | |
| PolyGRADRL Category=Model-Based RL2024.06 | 268.4 | |
| PETS-CEMRL Category=Model-Based RL2024.06 | 260.2 | |
| TRPORL Category=Model-Free RL2024.06 | 229.5 | |
| DeepSFRL Category=Representation RL2024.06 | 165.6 | |
| ME-TRPORL Category=Model-Based RL2024.06 | -1,609.3 |