# Calibration-First Reward-Component Auditing for Reinforcement Learning Control in Smart Greenhouses

arXiv: https://arxiv.org/abs/2607.11959 · HTML: https://mlsanity.com/paper/2607.11959/

## 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 11 of its 33 references that are in the map.
- First posted on arXiv 12 Jul 2026.

## Placed in

- Deep reinforcement learning methods / [RL for energy, networks and operations](https://mlsanity.com/deeprl/rl-for-energy-networks-and-operations/)

## Builds on (most cited first, 11 of 11)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World](https://mlsanity.com/paper/1703.06907/) (2017)
- [Verifiable Reinforcement Learning via Policy Extraction](https://mlsanity.com/paper/1805.08328/) (2018)
- [Explainable Reinforcement Learning: A Survey](https://mlsanity.com/paper/2005.06247/) (2020)
- [Robot Learning from Randomized Simulations: A Review](https://mlsanity.com/paper/2111.00956/) (2021)
- [Reinforcement Learning Versus Model Predictive Control on Greenhouse Climate Control](https://mlsanity.com/paper/2303.06110/) (2023)
- [Distributional Reward Decomposition for Reinforcement Learning](https://mlsanity.com/paper/1911.02166/) (2019)
- [Reinforcement Learning-based Model Predictive Control for Greenhouse Climate Control](https://mlsanity.com/paper/2409.12789/) (2024)
- [Robust Model-based Reinforcement Learning for Autonomous Greenhouse Control](https://mlsanity.com/paper/2108.11645/) (2021)
- [GreenLight-Gym: Reinforcement learning benchmark environment for control of greenhouse production systems](https://mlsanity.com/paper/2410.05336/) (2024)
- [Grower-in-the-Loop Interactive Reinforcement Learning for Greenhouse Climate Control](https://mlsanity.com/paper/2505.23355/) (2025)

## Abstract (arXiv)

Greenhouse reinforcement learning can test climate-control ideas at a speed and scale that is difficult to achieve with crop experiments alone. For smart-greenhouse control, however, a single simulator return is not enough: a grower or control engineer also needs to know when the policy heats, enriches CO2, vents, manages humidity, deploys screens, or uses lamps.We propose a reproducible calibration-first reward audit framework that keeps named greenhouse-control reward components comparable across simulator training, facility-adapted rollouts, logged Autonomous Greenhouse Challenge records, and actuator-rule distillation. In GreenLight-Gym, the framework decomposes the scalar reward into conditional temperature, CO2, humidity and vapor-pressure-deficit, screen, and actuation-proxy terms; adapts GreenLight to the second Autonomous Greenhouse Challenge logged climate traces; and scores the same components on logged greenhouse data.