3D on cartpole.swingup
Metric: Return (higher is better)
LeaderboardDataset
Loading chart...
Results
Submit a result| # | Model↕ | Return▼ | Augmentations | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | SMuZero | 868.87 | No | Learning and Planning in Complex Action Spaces | 2021-04-13 | Code |
| 2 | MuZero Unplugged | 594.3 | No | Online and Offline Reinforcement Learning by Pla... | 2021-04-13 | Code |