aRieL - Reinforcement Learning for the Ariel Space Telescope Scheduling
Abstract
The Ariel mission will conduct a population level survey of hundreds of exoplanet atmospheres, requiring observations to be scheduled across a large and diverse catalogue of potential targets. By framing Ariel scheduling as a long-horizon optimisation problem in which individual decisions affect both mission time and the scientific opportunities available later in the survey, Reinforcement Learning (RL) can be utilised as a framework for target selection. We introduce aRieL, a simulated observing environment coupled to a Set Transformer Proximal Policy Optimisation (PPO) agent that is trained to generate a scheduling policy. The RL policy consistently finds a strong compromise between competing survey objectives, producing large Tier~1 samples while maintaining high Tier~3 completion, population coverage, and observing efficiency when compared to a set of baseline heuristic polices. This behaviour is retained when the candidate catalogue is substantially expanded, while modifications to the reward function produce corresponding changes in the learned observing strategy. We further show that a policy trained on the baseline mission scenario can generalise without retraining to a modified scenario requiring repeated Tier~3 observations, revealing the resulting trade-off with the wider survey. These results demonstrate that reinforcement learning provides a flexible approach to large-scale astronomical scheduling, in which the observing strategy can respond directly to changes in mission state and to the scientific priorities, and motivate its wider exploration for observatories with similarly complex, state dependent scheduling problems.
Related
- Newly Identified Planetary Nebula Candidates in M31 using Deep-Learning Search of Hubble Space Telescope Images
- PSFSim: PhySics First Simulations for the Point Spread Function of the Roman Space Telescope
- Exploration of Exoplanet Atmospheres with the James Webb Space Telescope
- Nancy Grace Roman Space Telescope Wide Field Instrument: Grism Saturation Response to Bright Sources during Thermal-Vacuum Testing
- A New Era for Supernova Science with the James Webb Space Telescope
BibTeX
@misc{ray2026ariel,
title = {{aRieL - Reinforcement Learning for the Ariel Space Telescope Scheduling}},
author = {James Kostas Ray and Kai Hou Yip and Alexandra Thompson and Luís F. Simões and Nikolaos Nikolaou},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.38566},
eprint = {2609.38566},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.38566},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - UNPB
TI - aRieL - Reinforcement Learning for the Ariel Space Telescope Scheduling
AU - James Kostas Ray
AU - Kai Hou Yip
AU - Alexandra Thompson
AU - Luís F. Simões
AU - Nikolaos Nikolaou
PY - 2026
DA - 2026/09/29
PB - arXiv
DO - 10.48550/arxiv.2609.38566
UR - https://arxiv.org/abs/2609.38566
AB - The Ariel mission will conduct a population level survey of hundreds of exoplanet atmospheres, requiring observations to be scheduled across a large and diverse catalogue of potential targets. By framing Ariel scheduling as a long-horizon optimisation problem in which individual decisions affect both mission time and the scientific opportunities available later in the survey, Reinforcement Learning (RL) can be utilised as a framework for target selection. We introduce aRieL, a simulated observing environment coupled to a Set Transformer Proximal Policy Optimisation (PPO) agent that is trained to generate a scheduling policy. The RL policy consistently finds a strong compromise between competing survey objectives, producing large Tier~1 samples while maintaining high Tier~3 completion, population coverage, and observing efficiency when compared to a set of baseline heuristic polices. This behaviour is retained when the candidate catalogue is substantially expanded, while modifications to the reward function produce corresponding changes in the learned observing strategy. We further show that a policy trained on the baseline mission scenario can generalise without retraining to a modified scenario requiring repeated Tier~3 observations, revealing the resulting trade-off with the wider survey. These results demonstrate that reinforcement learning provides a flexible approach to large-scale astronomical scheduling, in which the observing strategy can respond directly to changes in mission state and to the scientific priorities, and motivate its wider exploration for observatories with similarly complex, state dependent scheduling problems.
ER -