Development of a Soft Actor Critic Deep Reinforcement Learning Approach for Harnessing Energy Flexibility in a Large Office Building.
Anjukan KathirgamanathanEleni E. ManginaDonal Patrick FinnPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- actor critic
- temporal difference
- policy gradient
- approximate dynamic programming
- function approximation
- reinforcement learning algorithms
- optimal control
- state space
- gradient method
- learning algorithm
- neuro fuzzy
- model free
- policy iteration
- mobile robot
- control problems
- optimal policy
- temporal difference learning
- supervised learning
- objective function