Openai Gym On Hopper V2
评估指标
Action Repetition
Average Decisions
Mean Reward
评测结果
各个模型在此基准测试上的表现结果
比较表格
| 模型名称 | Action Repetition | Average Decisions | Mean Reward |
|---|---|---|---|
| temporally-layered-architecture-for-efficient | .5722 | 423.91 | 3458.22 |
| advantage-weighted-regression-simple-and | - | - | 3405 |