Greenhouse Control Setpoints for Reinforcement Learning Benchmark

5.5 KB Excel file contains greenhouse climate control setpoints used to benchmark reinforcement learning algorithms. The dataset, authored by Iman Hindi and updated in March 2026, supports research on optimizing temperature, CO₂, and irrigation for crop yield and resource efficiency.

Use Cases

• Benchmark reinforcement learning algorithms like TD3 or PPO using the setpoint data to optimize greenhouse control policies.
• Analyze trade-offs between crop yield parameters (stem elongation, stem thickness, cumulative trusses) and resource consumption (heating, electricity, CO₂, irrigation) defined in the reward function.
• Simulate greenhouse environment interactions for an RL agent using setpoints for temperature, CO₂ concentration, and irrigation levels.

Strengths

• Dataset is recent, last updated in March 2026.
• Provides a benchmark for evaluating multiple RL algorithms (PPO, DDPG, SAC, TD3).
• Focuses on key agricultural control variables: temperature, CO₂ concentration, and irrigation.

Limitations

• Very small scale at only 5.5 KB, indicating limited data volume.
• Unknown row and column structure limits understanding of dataset scope and features.
• Derived from a simulated/virtual environment, which may not fully capture real-world greenhouse dynamics.

Provenance

Source

figshare

Collection Method

Generated as part of a reinforcement learning research framework for greenhouse climate control simulation.

Time Range

null

Freshness

2026-03-26

Geography

null