MPTCP energy enhancement paradox: A Q-learning approach.
Mohammad Javad ShamaniSaeid RezaeiGuillaume JourjonAruna SeneviratnePublished in: ITNAC (2017)
Keyphrases
- reinforcement learning
- energy minimization
- cooperative
- function approximation
- state space
- energy consumption
- multi agent
- image enhancement
- model free
- learning rate
- low energy
- minimum energy
- learning algorithm
- action selection
- reinforcement learning algorithms
- artificial neural networks
- optimal policy
- potential field
- credit assignment