随机方差缩减的递归动量策略梯度方法
Stochastic variance-reduced recursive momentum policy gradient method
随机方差缩减的递归动量策略梯度方法 |
| 辛垚辉,李永强,冯宇,胡磊 |
|
Stochastic variance-reduced recursive momentum policy gradient method |
| Yaohui XIN,Yongqiang LI,Yu FENG,Lei HU |
| 图 2 5种算法在连续任务上的奖励曲线 |
| Fig.2 Reward curves of 5 algorithms on continuous tasks |
|
|