{"id":"W4405464838","doi":"10.1145/3670865.3673644","title":"Understanding Iterative Combinatorial Auction Designs via Multi-Agent Reinforcement Learning","year":2024,"lang":"en","type":"article","venue":"","topic":"Auction Theory and Applications","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Simons Institute for the Theory of Computing, University of California Berkeley; Natural Sciences and Engineering Research Council of Canada; Defense Advanced Research Projects Agency; Canadian Institute for Advanced Research","keywords":"Reinforcement learning; Combinatorial auction; Computer science; Double auction; Artificial intelligence; Mathematical optimization; Common value auction; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001598624,0.0001063448,0.0001144536,0.0002108089,0.0005380149,0.0004988765,0.0001771881,0.00005578701,0.00252078],"category_scores_gemma":[0.0002345744,0.00007817691,0.00008958673,0.000698713,0.00007543459,0.0004520727,0.00005851903,0.0001919151,0.001539844],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002338728,"about_ca_system_score_gemma":0.00003915764,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007298359,"about_ca_topic_score_gemma":0.000002864834,"domain_scores_codex":[0.9983494,0.0001845293,0.0003949473,0.0003664777,0.0005483065,0.0001563936],"domain_scores_gemma":[0.9989555,0.0006038526,0.00007815004,0.0001923922,0.00008917967,0.00008087805],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002170766,0.00003520767,0.00007012462,0.000003404752,0.00003159946,0.000003243738,0.00232418,0.03991878,0.002423795,0.9474869,0.004425802,0.00325524],"study_design_scores_gemma":[0.0004228103,0.0001454419,0.00006297738,0.00002457929,0.00002180721,0.00001459514,0.007012872,0.4738,0.005112083,0.4480817,0.06505775,0.000243409],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001377624,0.00002409418,0.9861293,0.0005049419,0.001691674,0.0002043968,7.918869e-7,0.0002066643,0.009860517],"genre_scores_gemma":[0.9768108,0.00000531907,0.0008003882,0.00005450794,0.0001769944,0.00003241718,0.000005437848,0.000008667853,0.02210553],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9853289,"threshold_uncertainty_score":0.9992376,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3987536378951486,"score_gpt":0.4243150585242639,"score_spread":0.02556142062911526,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}