Grower-in-the-loop interactive reinforcement learning for greenhouse climate control

Climate control is crucial for greenhouse production as it directly affects crop growth and resource use. Reinforcement learning (RL) has received increasing attention in this field, but still faces challenges, including limited training efficiency and high reliance on initial learning conditions. Interactive RL, which integrates human (grower) input with the RL agent’s learning, offers a potential solution to overcome these challenges. However, interactive RL has not yet been applied to greenhouse climate control. Furthermore, human input is hardly perfect due to the complexity of climate control. The performance of interactive RL may also be limited by imperfect input. Therefore, this paper aims to explore the possibility and performance of applying interactive RL with imperfect inputs into greenhouse climate control, by: (1) developing three representative interactive RL algorithms tailored for greenhouse climate control (reward shaping, policy shaping and control sharing); (2) analyzing how input characteristics are often contradicting, and how the trade-offs between them make grower’s inputs difficult to perfect; (3) proposing a neural network-based approach to enhance the robustness of interactive RL agents under limited input availability; (4) conducting a comprehensive evaluation of the three interactive RL algorithms with imperfect inputs in a simulated greenhouse environment. The demonstration shows that interactive RL incorporating imperfect grower inputs has the potential to improve the performance of the RL agent. Interactive RL algorithms that influence action selection, such as policy shaping and control sharing, perform better when dealing with imperfect inputs, achieving 8.4% and 6.8% improvement in profit, respectively. In contrast, reward shaping, an algorithm that manipulates the reward function, is sensitive to imperfect inputs and leads to a 9.4% decrease in profit. This highlights the importance of selecting an appropriate mechanism when incorporating imperfect inputs. • An interactive RL framework to improve system efficiency and practical applicability. • Developed and tested three interactive RL methods to integrate growers’ expertise. • A neural network-based method enhances RL robustness under imperfect inputs. • Simulation results emphasize the critical role of input integration mechanisms.