Continuous Control 벤치마크
Continuous Control on cartpole.swingup
Return
- 2021-04-13 — SMuZero: Return 868.87
| Rank | Model | Return | Paper | Code | Year |
|---|---|---|---|---|---|
| 1 | SMuZero | 868.87 | Learning and Planning in Complex Action Spaces | opendilab/LightZero | 2021 |
| 2 | MuZero Unplugged | 594.3 | Online and Offline Reinforcement Learning by Planning with a Learned Model | DHDev0/Muzero-unplugged · enpasos/muzero | 2021 |
| 3 | SMuZero | 868.87 | Learning and Planning in Complex Action Spaces | opendilab/LightZero | 2021 |
| 4 | MuZero Unplugged | 594.3 | Online and Offline Reinforcement Learning by Planning with a Learned Model | DHDev0/Muzero-unplugged · enpasos/muzero | 2021 |
| 5 | SMuZero | 868.87 | Learning and Planning in Complex Action Spaces | opendilab/LightZero | 2021 |
| 6 | MuZero Unplugged | 594.3 | Online and Offline Reinforcement Learning by Planning with a Learned Model | DHDev0/Muzero-unplugged · enpasos/muzero | 2021 |