aiqbench analysis
The paper applies deep reinforcement learning to sequential price discovery in iterative combinatorial auctions, training recurrent graph policies offline so that each online price update needs only one forward pass. The reported gains are modest on the one-item experiment (expected rounds fall from 1.85 to 1.65) and rest on a 300-900x speedup in online price selection. Readers should note that the results come from a single experiment and benchmark suite, so generalization to real spectrum or procurement markets remains untested.
Fast Iterative Combinatorial Auctions via Deep Reinforcement Learning
arXiv:2610.30667v1 Announce Type: cross Abstract: Iterative combinatorial auctions are used in spectrum allocation, transportation, and industrial procurement, but rounds are costly. We introduce FastCombo, a deep reinforcement learning approach to sequential price discovery. Bayesian pricing has sharply reduced auction rounds even against subgradient benchmarks tuned with hindsight for each instance, but relies on a one-step objective and repeated online inference and optimization. We prove that greedily maximizing immediate clearing probability can require arbitrarily more rounds in expectation than an informative policy, even with the true valuation distribution known. FastCombo learns price policies offline, assigning credit to queries for the future decisions they enable and producing each online price update with a single neural-network forward pass. We formulate the objective of minimizing expected rounds to clearing in single-minded auctions as a partially observable Markov decision process and train a recurrent bidder-item graph policy over complete auction trajectories. In a one-item experiment, all five trained policies learn an informative opening, reducing expected rounds from 1.85 to 1.65 relative to the tested Bayesian one-step rule. Across four domains from the Combinatorial Auction Test Suite, FastCombo achieves competitive clearing while reducing measured online price-selection time per auction by a factor of roughly 300-900 relative to the standard Bayesian baseline. These results demonstrate the value of learning sequential price policies for both information acquisition and online computational efficiency.
Abstract:Iterative combinatorial auctions are used in spectrum allocation, transportation, and industrial procurement, but rounds are costly. We introduce FastCombo, a deep reinforcement learning approach to sequential price discovery. Bayesian pricing has sharply reduced auction rounds even against subgradient benchmarks tuned with hindsight for each instance, but relies on a one-step objective and repeated online inference and optimization. We prove that greedily maximizing immediate clearing probability can require arbitrarily more rounds in expectation than an informative policy, even with the true valuation distribution known. FastCombo learns price policies offline, assigning credit to queries for the future decisions they enable and producing each online price update with a single neural-network forward pass. We formulate the objective of minimizing expected rounds to clearing in single-minded auctions as a partially observable Markov decision process and train a recurrent bidder-item graph policy over complete auction trajectories. In a one-item experiment, all five trained policies learn an informative opening, reducing expected rounds from 1.85 to 1.65 relative to the tested Bayesian one-step rule. Across four domains from the Combinatorial Auction Test Suite, FastCombo achieves competitive clearing while reducing measured online price-selection time per auction by a factor of roughly 300-900 relative to the standard Bayesian baseline. These results demonstrate the value of learning sequential price policies for both information acquisition and online computational efficiency.
Computer Science and Game Theory (cs.GT); Machine Learning (cs.LG)
arXiv:2610.30667 [cs.GT]
(or arXiv:2610.30667v1 [cs.GT] for this version)
https://doi.org/10.48550/arXiv.2610.30667 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 318 words
Related coverage
Latent Spherical Flow Policy for Reinforcement Learning with Combinatorial Actions
arXiv · Jun 9, 2026
Black-Box Combinatorial Optimization with Order-Invariant Reinforcement Learning
arXiv · Nov 3, 2026
Geometry-Aware Reinforcement Learning for 2D Irregular Nesting
arXiv · Sep 21, 2026
Geometry-Aware Reinforcement Learning for 2D Irregular Nesting
arXiv · Jun 10, 2026