From: Network resource optimization with reinforcement learning for low power wide area networks
Hyperparameters | Values |
---|---|
Replay buffer size | 50 |
Minibatch size | 8 |
Activation function | Relu |
Optimizer | Adam |
Learning rate | 0.01 |
Epsilon decay | 0.99 |
Hidden layers | 30×58 |
Learning time (hours) | 10 |