Evaluating Meta-Reinforcement Learning through a HVAC Control Benchmark (Student Abstract)


  • Yashvir S. Grewal Monash University, Australia
  • Frits de Nijs Monash University, Australia
  • Sarah Goodwin Monash University, Australia


Reinforcement Learning, Meta Reinforcement Learning, Benchmarks, Energy, Heating Ventilation And Airconditioning Control, Energy Markets


Meta-Reinforcement Learning (RL) algorithms promise to leverage prior task experience to quickly learn new unseen tasks. Unfortunately, evaluating meta-RL algorithms is complicated by a lack of suitable benchmarks. In this paper we propose adapting a challenging real-world heating, ventilation and air-conditioning (HVAC) control benchmark for meta-RL. Unlike existing benchmark problems, HVAC control has a broader task distribution, and sources of exogenous stochasticity from price and weather predictions which can be shared across task definitions. This can enable greater differentiation between the performance of current meta-RL approaches, and open the way for future research into algorithms that can adapt to entirely new tasks not sampled from the current task distribution.




How to Cite

Grewal, Y. S., de Nijs, F., & Goodwin, S. (2021). Evaluating Meta-Reinforcement Learning through a HVAC Control Benchmark (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence, 35(18), 15785-15786. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/17889



AAAI Student Abstract and Poster Program