Omniverse Isaac Gym On Anymal
評価指標
Average 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 | Average Return | Paper Title | Repository |
|---|---|---|---|
| MEow | 47.62 | Maximum Entropy Reinforcement Learning via Energy-Based Normalizing Flow | |
| SAC | 11.87 | Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor |
0 of 2 row(s) selected.