{"id":"W4318350404","doi":"10.48550/arxiv.2301.11181","title":"Deep Laplacian-based Options for Temporally-Extended Exploration","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; DeepMind","keywords":"Laplacian matrix; Computer science; Reinforcement learning; Eigenfunction; Scalability; Variety (cybernetics); Laplace operator; Artificial intelligence; Graph; Machine learning; Mathematical optimization; Theoretical computer science; Eigenvalues and eigenvectors; Mathematics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00112903,0.0007975815,0.001027539,0.0008943046,0.0004964636,0.001201227,0.001779472,0.001475955,0.003771407],"category_scores_gemma":[0.006457096,0.0006172812,0.0008178054,0.0006690297,0.001291728,0.002759935,0.002362602,0.002074433,0.0005566821],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001010164,"about_ca_system_score_gemma":0.001035815,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002469601,"about_ca_topic_score_gemma":0.003904391,"domain_scores_codex":[0.9995448,0.0001462374,0.00002562552,0.0001083693,0.0001051815,0.00006972704],"domain_scores_gemma":[0.9977382,0.001541263,0.000180168,0.0001989772,0.0001735578,0.0001678409],"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":[0.0002290545,0.0001135528,0.002069387,0.0001120262,0.00005895164,0.00014079,0.0001898378,0.833387,0.00303668,0.05105341,0.003005473,0.106604],"study_design_scores_gemma":[0.000008771837,0.00001562781,0.00007151453,0.000008586183,0.000003232652,0.00001451092,0.000009256022,0.9751081,0.0003063239,0.0241794,0.0002691371,0.000005507644],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03816612,0.000399737,0.9577094,0.000477037,0.0000321047,0.0000520905,0.0001523985,0.0007178101,0.002293394],"genre_scores_gemma":[0.8032027,0.000306577,0.1911298,0.000279024,0.000049748,0.0002075539,0.0003584289,0.0001856972,0.004280481],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003771407,"threshold_uncertainty_score":0.01261657,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.459823302277091,"score_gpt":0.3541716124842355,"score_spread":0.1056516897928556,"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."}}