New Offline Learning Algorithm Improves Multi-User Scheduling Without Real-Time System Testing
Researchers have introduced SOCD, an offline reinforcement learning algorithm that learns efficient multi-user delay-constrained scheduling policies entirely from pre-collected data, without requiring live system interactions during training. The work targets applications such as embodied AI, instant messaging, live streaming, and data center management, where real-time resource allocation among users with varying delay sensitivities is critical. The approach addresses a key practical barrier of existing learning-based schedulers, which can degrade live system performance during training.
A research team has proposed SOCD (Scheduling By Offline Learning with Critic Guidance and Diffusion Model), a novel algorithm designed to solve multi-user delay-constrained scheduling problems using only pre-collected offline data. Unlike current learning-based scheduling methods that require online interaction with live systems—risking service degradation and significant operational costs—SOCD trains entirely offline. The algorithm combines a diffusion policy with a sampling-free critic network for policy guidance, and integrates Lagrangian multiplier optimization to handle resource and delay constraints efficiently. Experimental results indicate that SOCD is robust across a range of system dynamics, including partially observable and large-scale environments, and outperforms existing baseline methods. The work was submitted to arXiv in January 2025 and updated in June 2026, and is categorized under Artificial Intelligence.
What's missing
The paper does not detail the specific datasets used for offline training, their provenance, or how representative they are of real-world deployment conditions—a key open question for offline RL generalization. The degree to which performance gains hold in true production environments versus simulated benchmarks is not fully established. Additionally, computational overhead of the diffusion model component relative to simpler baselines is not discussed in the abstract.
What different sources said
- arXiv cs.AICenter
Offline Diffusion Policy for Multi-User Delay-Constrained Scheduling
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.