Open Access
表4
TD3算法主要超参数的取值
| 参数 | 值 |
| Critic网络1学习率 | 1×10-4 |
| Critic网络2学习率 | 5×10-5 |
| Actor网络学习率 | 1×10-5 |
| Actor延迟更新步数 | 2 |
| Actor噪声方差 | 0.1 |
| Actor噪声衰减率 | 0.05 |
| 奖励系数 | 1 |
| Q值折扣因子 | 0.99 |
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.