{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002743212,0.0002526398,0.0002991243,0.0002683831,0.0002618823,0.0003504808,0.00120195,0.0001839351,0.00002351343],"category_scores_gemma":[0.00004830542,0.0002900049,0.0002233012,0.0005360885,0.00005901498,0.0003478015,0.002024018,0.000533113,0.000009229515],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001503317,"about_ca_system_score_gemma":0.0002248313,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001399031,"about_ca_topic_score_gemma":0.00003338333,"domain_scores_codex":[0.9982505,0.0001319722,0.0002294174,0.0008414699,0.0001220539,0.0004245414],"domain_scores_gemma":[0.9985294,0.00007484768,0.0002123117,0.0007261373,0.0002791207,0.0001781239],"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":[0.000008320009,0.00008091801,0.00009859873,0.0001176857,0.00005751546,0.00001322256,0.001111386,0.8910027,0.00001356492,0.1072115,0.00003488003,0.0002497267],"study_design_scores_gemma":[0.0004222692,0.00005392977,0.00004515289,0.00005585666,0.00002388083,0.000002307282,0.0004025928,0.9927093,0.00002572224,0.004943858,0.001005251,0.0003099208],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01542143,0.00005070342,0.9808621,0.0001812474,0.000183493,0.0004725811,0.00000309186,0.0002500392,0.002575275],"genre_scores_gemma":[0.9066533,0.000290246,0.08632229,0.0002337908,0.00007118089,0.000005692518,0.0002446524,0.00002288435,0.006155937],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8945398,"threshold_uncertainty_score":0.9999552,"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."}}