Command Palette
Search for a command to run...
Continuous Control On Cartpole Swingup 2
평가 지표
Return
평가 결과
이 벤치마크에서 각 모델의 성능 결과
| Paper Title | ||
|---|---|---|
| SMuZero | 868.87 | Learning and Planning in Complex Action Spaces |
| MuZero Unplugged | 594.3 | Online and Offline Reinforcement Learning by Planning with a Learned Model |
0 of 2 row(s) selected.