Refine
Year of publication
- 2013 (1) (remove)
Document Type
- Conference Proceeding (1) (remove)
Language
- English (1) (remove)
Has Fulltext
- no (1)
Is part of the Bibliography
- no (1)
Keywords
- Approximate dynamic program (1)
- Heating control (1)
- Home Automation (1)
- Reward Function (1)
- Target Temperature (1)
Institute
We propose a reinforcement learning approach to heating control in home automation, that can acquire a set of rules enabling an agent to heat a room to the desired temperature at a defined time while conserving as much energy as possible. Experimental results are presented that show the feasibility of our method.