Advances, Systems and Applications
From: MRLCC: an adaptive cloud task scheduling method based on meta reinforcement learning
Hyperparameter | Value |
---|---|
lay1 | 256 |
lay2 | 128 |
lay3 | 64 |
activation function1,2 | Tanh |
activation function3 | Softmax |
optimization method | Adam |
learning rate \(\alpha\) | 3\(\times 10^{-4}\) |
learning rate \(\beta\) | 3\(\times 10^{-4}\) |
discount factor \(\gamma\) | 0.99 |