Results of the summarizing process for the arXiv paper: 2305.00365v1

Smart buildings aim to optimize energy consumption by using artificial intelligent algorithms. However, when a smart building is commissioned, there is no historical data available to train these algorithms. Online Reinforcement Learning (RL) algorithms have shown promise in this regard, but their deployment carries a risk as the RL agent explores its action space and potentially causes discomfort to the building residents. To address this issue, the authors propose a new technique called ReLBOT. ReLBOT utilizes transfer learning in conjunction with deep RL to transfer knowledge from an existing optimized smart building to a newly commissioned one. By doing so, it aims to reduce the adverse impact of the reinforcement learning agent's warm-up period. The authors demonstrate significant improvements through ReLBOT, including up to 6.2 times reduction in duration and up to 132 times reduction in prediction variance for the reinforcement learning agent's warm-up period. This research by Mikhail Genkin and J.J. McArthru presents an innovative approach that addresses the challenges faced during the initial exploration phase of RL algorithms in smart buildings. By leveraging transfer learning and deep RL techniques, ReLBOT offers a solution that minimizes risks while optimizing energy consumption. This paper contributes valuable insights into improving the efficiency and effectiveness of smart buildings through AI-driven algorithms by reducing risks associated with online reinforcement learning agents' warm-up periods while also optimizing energy consumption levels.

• Smart buildings aim to optimize energy consumption using AI algorithms
• Lack of historical data for training these algorithms during commissioning
• Online reinforcement learning (RL) algorithms show promise but carry risk of discomfort to residents
• Proposed technique called ReLBOT utilizes transfer learning and deep RL
• ReLBOT transfers knowledge from an existing optimized smart building to a newly commissioned one
• Aims to reduce adverse impact of RL agent's warm-up period
• Significant improvements demonstrated, including reduction in duration and prediction variance
• Research addresses challenges in initial exploration phase of RL algorithms in smart buildings
• ReLBOT minimizes risks while optimizing energy consumption levels through AI-driven algorithms.

Smart Buildings and Artificial Intelligence: Leveraging Transfer Learning and Deep RL to Optimize Energy Consumption

Smart buildings are becoming increasingly popular as they offer a range of benefits, including energy efficiency, improved comfort levels, and cost savings. To achieve these goals, smart buildings rely on artificial intelligence algorithms that can optimize their energy consumption. However, when a smart building is commissioned there is no historical data available to train these algorithms. This presents a challenge for the optimization process as it requires an exploration period where the AI agent learns from its environment in order to make effective decisions.

Online Reinforcement Learning (RL) algorithms have been proposed as a solution to this problem; however, their deployment carries risks due to the fact that the RL agent explores its action space which could potentially cause discomfort to building residents. To address this issue, researchers Mikhail Genkin and J.J. McArthru propose ReLBOT – a new technique that utilizes transfer learning in conjunction with deep RL in order to transfer knowledge from an existing optimized smart building to newly commissioned ones.

What is Transfer Learning?

Transfer learning is an approach used in machine learning that allows knowledge acquired by one model or system (the source model) to be transferred and applied towards another model or system (the target model). In other words, it enables models trained on different datasets or tasks to share information so that they can better understand each other’s data patterns without having access to all of the same training data points.

How Does ReLBOT Work?

ReLBOT works by leveraging transfer learning techniques combined with deep reinforcement learning (RL). It transfers knowledge from an existing optimized smart building (the source model) into a newly commissioned one (the target model). By doing so, it aims at reducing the adverse impact of the reinforcement learning agent's warm-up period while also optimizing energy consumption levels within both buildings simultaneously. The authors demonstrate significant improvements through ReLBOT including up 6.2 times reduction in duration and up 132 times reduction in prediction variance for the reinforcement learning agent's warm-up period compared with traditional methods such as online Q-learning or offline supervised training approaches alone .

Conclusion

This research paper offers valuable insights into improving efficiency and effectiveness of smart buildings through AI-driven algorithms by reducing risks associated with online reinforcement learning agents' warm-up periods while also optimizing energy consumption levels at both existing and newly commissioned sites simultaneously using transfer learning techniques combined with deep RL methods such as ReLBOT proposed by Mikhail Genkin and J.J McArthru .