{"id":"W3199020031","doi":"10.48550/arxiv.2109.10380","title":"Deep Policies for Online Bipartite Matching: A Reinforcement Learning Approach","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Optimization and Search Problems","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Bipartite graph; Computer science; Matching (statistics); Reinforcement learning; Submodular set function; Machine learning; Set (abstract data type); Code (set theory); Artificial intelligence; Feature (linguistics); Process (computing); Variety (cybernetics); Greedy algorithm; Data mining; Theoretical computer science; Mathematical optimization; Algorithm; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003410739,0.001105163,0.001731674,0.0009791781,0.0005949714,0.001103502,0.00280886,0.002025443,0.004014047],"category_scores_gemma":[0.01327256,0.0007418183,0.0006941642,0.001165513,0.001892564,0.002943498,0.001988071,0.003168839,0.000707841],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002085822,"about_ca_system_score_gemma":0.002390696,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005371768,"about_ca_topic_score_gemma":0.006209849,"domain_scores_codex":[0.9985331,0.0006305081,0.00006721335,0.0003616078,0.000216051,0.000191446],"domain_scores_gemma":[0.9941676,0.004214873,0.0004298477,0.000521537,0.0004021723,0.0002640676],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001127222,0.0001714958,0.0009194961,0.00007717047,0.00003885989,0.00004174174,0.00005609909,0.9216793,0.0005703573,0.02386515,0.002128829,0.05033885],"study_design_scores_gemma":[0.000009910841,0.00001230893,0.00003080543,0.000004835924,0.000002752472,0.000004490591,0.000003344627,0.98698,0.0001305995,0.01265173,0.0001669077,0.000002431185],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02454085,0.0003201613,0.9710656,0.0006382999,0.00004781755,0.00009809822,0.0001313984,0.0007663675,0.002391367],"genre_scores_gemma":[0.7846472,0.0003171171,0.2092734,0.0005347788,0.00008388574,0.000360845,0.000424424,0.0002182947,0.004140063],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005371768,"threshold_uncertainty_score":0.01803792,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1036813019083631,"score_gpt":0.2251592190344957,"score_spread":0.1214779171261326,"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."}}