Continuous Control On Deepmind Walker Walk
評価指標
Return
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
モデル名 | Return | Paper Title | Repository |
|---|---|---|---|
| PlaNet | 890 | Learning Latent Dynamics for Planning from Pixels | |
| DrQ | 921 | Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels |
0 of 2 row(s) selected.