Addressing partial observability in reinforcement learning for energy management.
Marco BiemannXiufeng LiuYifeng ZengLizhen HuangPublished in: BuildSys@SenSys (2021)
Keyphrases
- partial observability
- energy management
- reinforcement learning
- partially observable
- power consumption
- energy saving
- belief space
- markov decision process
- power saving
- function approximation
- learning agent
- state space
- partially observable markov decision processes
- machine learning
- belief state
- energy efficiency
- smart home
- planning problems
- electric vehicles
- learning algorithm
- reinforcement learning algorithms
- transfer learning
- dynamic programming
- partial information
- reward function
- model free
- learning process
- expert systems
- artificial intelligence