Baseline-Free Policy Optimization Shows Promise for Neural Combinatorial Optimization
Researchers evaluated Group Relative Policy Optimization (GRPO), a baseline-free algorithm from large language model alignment, for training neural combinatorial optimization models on routing problems like TSP and CVRP. GRPO eliminates the need for maintaining a frozen policy copy for variance reduction, addressing a structural vulnerability in standard REINFORCE training that causes performance collapse on harder instances. The findings suggest GRPO could improve training stability and efficiency in combinatorial optimization tasks.
A new arXiv preprint evaluates GRPO, an algorithm originally developed for large language model alignment, as an alternative to standard REINFORCE-based training for neural combinatorial optimization (NCO). The standard approach uses a rollout baseline—a frozen copy of the policy—for variance reduction, but this introduces instability on harder problem instances. The researchers conducted controlled comparisons of five RL algorithms on Traveling Salesman Problem (TSP) and Capacitated Vehicle Routing Problem (CVRP) benchmarks using the RL4CO framework. GRPO avoids the training collapse observed with REINFORCE on TSP-100, where performance degraded from cost 9.8 to 52.1 after the warmup phase. At matched gradient updates, GRPO achieved solution quality within 2% of POMO, a strong multi-start baseline, without requiring an external baseline. A second algorithm tested, P3O (pairwise preference optimization), was competitive on TSP but showed higher variability on CVRP.
What's missing
The study does not discuss computational cost comparisons between GRPO and baseline-dependent methods, nor does it address scalability to larger problem instances or real-world applications beyond the benchmarks tested.
What different sources said
- arXiv cs.LGCenter
Baseline-Free Policy Optimization for Neural Combinatorial Optimization
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.