Openai Gym On Hopper V2
評価指標
Action Repetition
Average Decisions
Mean Reward
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 | Action Repetition | Average Decisions | Mean Reward | Paper Title | Repository |
|---|---|---|---|---|---|
| TLA | .5722 | 423.91 | 3458.22 | Optimizing Attention and Cognitive Control Costs Using Temporally-Layered Architectures | |
| AWR | - | - | 3405 | Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning |
0 of 2 row(s) selected.