1. Constrained markov decision processes;Altnan,1999
2. Thermal environmental conditions for human occupancy;ASHRAE Standard 55,2017
3. User comfort and energy efficiency in HVAC systems by Q-learning;Baghaee;2018 26th Signal Processing and Communications Applications Conference (SIU),2018
4. Autonomous HVAC control, a reinforcement learning approach;Barrett,2015
5. A Markovian decision process;Bellman;Indiana University Mathematics Journal,1957