Open Access

表2

算法训练超参数

初始状态 参数描述 数值区间
γ 折扣因子 0.95
DM 经验池大小 30 000
τ 软更新率 0.01
BatchSize 批样本数 512
αc Critic网络学习率 0.003
αu Actor网络学习率 0.001
ΔT/s 仿真步长 0.1
MaxStep 单回合最大时间步 5 000
MaxEpisode 训练回合数 1 000

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.