Control With Prametrised Actions On Half
評価指標
Goal Probability
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 | Goal Probability | Paper Title | Repository |
|---|---|---|---|
| Hybrid SAC | 0.639 | Discrete and Continuous Action Representation for Practical RL in Video Games | |
| MP-DQN | 0.913 | Multi-Pass Q-Networks for Deep Reinforcement Learning with Parameterised Action Spaces |
0 of 2 row(s) selected.