Adaptive multi-layer reward based Q-learning for source tracing in diffusive molecular communications environment with obstacles.
Zhibo LouWence ZhangXu BaoPublished in: Nano Commun. Networks (2023)
Keyphrases
- multi layer
- reinforcement learning
- feed forward neural networks
- neural nets
- learning agent
- error back propagation
- neural network
- agent receives
- dynamic environments
- single layer
- multi agent
- state space
- reward function
- multiple layers
- function approximation
- agent learns
- model free
- mobile robot
- multiscale
- learning algorithm
- genetic algorithm