Accelerated Variant of Reinforcement Learning Algorithms for Light Control with Non-stationary User Behaviour.
Nassim HaddamBenjamin Cohen BoulakiaDominique BarthPublished in: SMARTGREENS (2022)
Keyphrases
- non stationary
- user behaviour
- reinforcement learning algorithms
- reinforcement learning
- state space
- markov decision processes
- reinforcement learning problems
- model free
- function approximation
- temporal difference
- reward function
- user profiles
- empirical mode decomposition
- user preferences
- control problems
- user actions
- hidden markov models
- multiscale