Reinforcement Learning on Reacher
-4.1Average ReturnBest MBBL
Evaluation Results
| Method | Links | |
|---|---|---|
| Best MBBLRL Category=Model-Based RL, Steps=200K2024.06 | -4.1 | |
| LV-RepRL Category=Representation RL, Steps=200K2024.06 | -5.8 | |
| Diff-SRRL Category=Representation RL, Steps=200K2024.06 | -6.5 | |
| SPEDERL Category=Representation RL, Steps=200K2024.06 | -7.2 | |
| SACRL Category=Model-Free RL, Steps=200K2024.06 | -8.4 | |
| TRPORL Category=Model-Free RL, Steps=200K2024.06 | -10.1 | |
| PETS-CEMRL Category=Model-Based RL, Steps=200K2024.06 | -12.3 | |
| ME-TRPORL Category=Model-Based RL, Steps=200K2024.06 | -13.4 | |
| DeepSFRL Category=Representation RL, Steps=200K2024.06 | -16.8 | |
| PPORL Category=Model-Free RL, Steps=200K2024.06 | -17.2 | |
| PolyGRADRL Category=Model-Based RL, Steps=200K2024.06 | -20.7 | |
| PETS-RSRL Category=Model-Based RL, Steps=200K2024.06 | -40.1 |