mlsanityData to 14 Oct 2026

Safe Greenhouse Climate Control Using Lagrangian-Constrained PPO with Kolmogorov-Arnold Networks

arXiv 2609.34966 ↗First posted 28 Sep 2026cs.AIcited by 0

On the map: Deep reinforcement learning methods → RL for energy, networks and operations

Abstract (arXiv)

Greenhouse climate control balances economic return with maintaining temperature, humidity and CO2 within crop-adapted growth ranges. Conventional reinforcement learning (RL) greenhouse controllers use fixed reward penalties to limit climate constraint violations, yet such heuristic penalties cannot explicitly constrain long-term cumulative violations. Poorly tuned weights either lead to overly conservative policies and lower yields, or fail to suppress persistent climate deviations that harm photosynthesis and induce crop diseases. To address this issue, we formulate greenhouse climate regulation as a Constrained Markov Decision Process (CMDP) and use a Lagrangian safe RL framework RCPO-PPO to separate economic optimization and cumulative safety constraints, enabling adaptive penalty adjustment without manual tuning. To handle strong nonlinear, time-varying coupling between greenhouse microclimate and crop growth, Kolmogorov-Arnold Networks (KANs) replace Multi-Layer Perceptrons (MLPs) as policy and value approximators for improved nonlinear representation. Sinusoidal cyclic time features are embedded in observations to capture diurnal environmental periodicity. Simulations use a classic winter lettuce greenhouse model driven by 40-day real weather disturbances. Compared with vanilla penalty-based PPO, our method cuts cumulative climate violations by 18.65% and raises lettuce economic profit by 2.91%, keeping violations stable near the safety threshold. This decoupled CMDP optimization with KAN-based policy representation mitigates long-term climate risks and boosts planting profits, offering a constraint-aware control strategy for precision greenhouse cultivation.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL for energy, networks and operations, one of 15 directions in Deep reinforcement learning methods. Builds on 15 of its 40 references that are in the map. First posted on arXiv 28 Sep 2026.

Builds on

15 of 40 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025Grower-in-the-Loop Interactive Reinforcement Learning for Greenhouse Climate Control29 May
  2. 2024Reinforcement Learning-based Model Predictive Control for Greenhouse Climate Control19 Sep

Other references · 13

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2024KAN: Kolmogorov-Arnold Networkscited by 649
  3. 2018Reward Constrained Policy Optimizationcited by 417
  4. 2020Safe Reinforcement Learning in Constrained Markov Decision Processescited by 115
  5. 2020Safe Reinforcement Learning for Autonomous Vehicles through Parallel Constrained Policy Optimizationcited by 35
  6. 2023A Human-Centered Safe Robot Reinforcement Learning Framework with Interactive Behaviorscited by 15
  7. 2025A Survey of Safe Reinforcement Learning and Constrained MDPs: A Technical Survey on Single-Agent and Multi-Agent Safetycited by 13
  8. 2023Reinforcement Learning Versus Model Predictive Control on Greenhouse Climate Controlcited by 12
  9. 2024Kolmogorov-Arnold Network for Online Reinforcement Learningcited by 9
  10. 2023ROSARL: Reward-Only Safe Reinforcement Learningcited by 5
  11. 2022Coordinated Frequency Control through Safe Reinforcement Learningcited by 4
  12. 2025Safety Representations for Safer Policy Learningcited by 4
1 more
  1. 2025A Review On Safe Reinforcement Learning Using Lyapunov and Barrier Functionscited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025A Teacher-Student MPC-PPO Coupled Reinforcement Learning Framework for Winter Temperature Control of Solar Greenhouses in Northern China
  2. 2024Learning-based agricultural management in partially observable environments subject to climate variability
  3. 2024Intelligent Agricultural Management Considering N2O Emission and Climate Variability with Uncertainties
  4. 2024GreenLight-Gym: Reinforcement learning benchmark environment for control of greenhouse production systems
  5. 2025RL-Guided MPC for Autonomous Greenhouse Control
  6. 2026Calibration-First Reward-Component Auditing for Reinforcement Learning Control in Smart Greenhouses
  7. 2026Improving greenhouse fruit-production control by integrating reinforcement learning into short-horizon model predictive control
  8. 2024A Comparative Study of Deep Reinforcement Learning for Crop Production Management