First On-Sky Demonstration of Reinforcement Learning for Adaptive Optics Control
Researchers deployed a reinforcement learning-based adaptive optics controller called PO4AO on a 1.52-meter telescope and demonstrated it outperformed traditional control methods across multiple observing conditions. The system successfully learned to compensate for vibrations and noise while operating with a single set of hyperparameters. This represents the first validated on-sky test of RL for adaptive optics, potentially opening new approaches for telescope systems worldwide.
Scientists have achieved the first on-sky demonstration of a reinforcement learning controller for adaptive optics, named Policy Optimization for AO (PO4AO), deployed on the Papyrus adaptive optics system at the 1.52-meter telescope at Observatoire de Haute-Provence. The RL-based controller was compared against a standard integrator controller over multiple nights across varying flux levels and atmospheric conditions, consistently outperforming the baseline approach. PO4AO successfully learned and compensated for vibration patterns while demonstrating robustness to measurement noise, and operated in a turnkey fashion using a single hyperparameter set across different observing conditions and targets. The achievement is notable because while RL algorithms had shown promise in simulations and laboratory settings for handling real-world effects like photon noise, detector noise, and rapid atmospheric variations, their on-sky performance had never been validated until now. The researchers note that despite a non-optimized Python implementation introducing latency and occasional frame drops, the system performed well, suggesting that properly optimized implementations could enable broader adoption of RL strategies in adaptive optics operations.
What's missing
The study does not discuss computational requirements or cost comparisons between RL-based and traditional controllers, nor does it address scalability to larger telescope arrays or multi-conjugate adaptive optics systems. The paper also does not provide detailed comparison metrics (e.g., Strehl ratio improvements, specific performance gains in numerical terms) in the abstract.
What different sources said
- arXiv cs.LGCenter
On-sky demonstration of reinforcement learning for adaptive optics control
Related
Gut Bacteria Enzyme Found to Break Down Heat-Processed Food Compounds, Producing Novel Biogenic Amines
Researchers have discovered that an enzyme in common gut bacteria can degrade N-epsilon-carboxymethyllysine (CML), a compound formed during thermal food processing, producing previously unknown biogenic amines. The enzyme, ornithine decarboxylase SpeC from enterobacteria, acts on CML and related modified lysine derivatives through a low-level 'underground' catalytic activity. This finding suggests a previously unrecognized communication axis between thermally processed dietary compounds and gut microbial physiology, with potential implications for host health.
Full-Length Gene Sequencing Reveals Two Distinct Bacterial Communities in Black-Legged Ticks Expanding Into Canada
Researchers used Oxford Nanopore full-length 16S rRNA gene sequencing to characterize the microbiome of Ixodes scapularis black-legged ticks collected in Nova Scotia, Canada, distinguishing between tick-adapted bacteria and environmentally acquired bacteria. The study comes as I. scapularis — the primary vector of Lyme disease — is rapidly expanding northward into Canada due to climate change. The findings suggest that environmentally derived bacteria in tick microbiomes are not mere contamination, which has implications for how tick microbiome data is collected and interpreted across surveillance studies.
Study Identifies Metabolic Link Between Cell Envelope Stress and Biofilm Formation in Bacteria
Researchers have discovered that the metabolite acetyl-CoA directly inhibits enzymes that degrade the bacterial signaling molecule c-di-GMP, connecting cell envelope biosynthesis stress to biofilm formation in Pseudomonas aeruginosa. The study found that sub-inhibitory concentrations of antibiotics targeting early peptidoglycan biosynthesis — but not other antibiotic classes — elevate c-di-GMP levels by reducing phosphodiesterase activity, with acetyl-CoA competing for the enzyme active site. Because the relevant enzyme domain is broadly conserved across bacterial species, this checkpoint mechanism may be widespread and could have implications for understanding antibiotic-induced biofilm responses.