Sequential Resource Trading Using Comparison-Based Gradient Estimation

arXiv:2408.11186v4 Announce Type: replace-cross Abstract: We study sequential multi-issue trading between two greedily rational agents who exchange resources from a finite set of categories. Each agent's utility depends on its allocation, but the offering agent does not know the responding agent's utility function and receives only accept or reject feedback. We propose a comparison-based algorithm that interprets acceptance and rejection responses as pairwise state comparisons, allowing the offe