Controlling Action Space of Reinforcement-Learning-Based Energy Management in Batteryless Applications.
Junick AhnDaeyong KimRhan HaHojung ChaPublished in: IEEE Internet Things J. (2023)
Keyphrases
- action space
- energy management
- reinforcement learning
- state space
- markov decision processes
- state and action spaces
- continuous state
- power consumption
- real valued
- action selection
- power saving
- continuous state spaces
- stochastic processes
- state action
- reinforcement learning methods
- smart home
- function approximation
- electric vehicles
- energy saving
- single agent
- energy efficiency
- markov decision process
- reinforcement learning algorithms
- optimal policy
- markov decision problems
- learning algorithm
- model free
- transfer learning
- dynamic programming
- multi agent
- infinite horizon
- planning problems
- energy consumption
- multi agent systems
- machine learning