Reinforcement learning for energy harvesting point-to-point communications.
Andrea OrtizHussein Al-ShatriXiang LiTobias WeberAnja KleinPublished in: ICC (2016)
Keyphrases
- reinforcement learning
- energy consumption
- function approximation
- learning process
- reinforcement learning algorithms
- energy minimization
- state space
- model free
- low energy
- solar energy
- function approximators
- multi agent
- markov decision processes
- database
- communication networks
- communication systems
- markov decision process
- temporal difference
- minimum energy
- learning problems
- energy efficient
- energy efficiency
- transfer learning
- optimal policy
- sensor networks
- dynamic programming
- decision making
- information systems
- data sets