how to write DDPG Algorithm at case of L2 Regularization, ADAM Optimization and Number-of-steps-to-look-ahead ?
2 次查看(过去 30 天)
显示 更早的评论
I would like to inquiry how to write the DDPG algorithm if L2 Regularization, ADAM optimization and certain number of steps to look ahead exist in the code ?
i want to know the whole sequence in details like :
1- how the transitions are stored in replay buffer based on certain number of steps to look ahead
2- how could be the shape of cost function if L2 Regularization exist
3- how does adam optimizer works at this case
0 个评论
回答(0 个)
另请参阅
类别
在 Help Center 和 File Exchange 中查找有关 Statistics and Machine Learning Toolbox 的更多信息
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!