{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002064287,0.0003731028,0.0005363923,0.001288849,0.0004850696,0.0003450743,0.002047963,0.0004262273,0.0002042449],"category_scores_gemma":[0.002665889,0.0003811176,0.0004816786,0.001923741,0.0002629549,0.0007251717,0.0008495601,0.0006499387,0.001147097],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003872379,"about_ca_system_score_gemma":0.0005825934,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006185233,"about_ca_topic_score_gemma":0.0005374281,"domain_scores_codex":[0.9960252,0.0003543747,0.0005577599,0.001827406,0.0006482616,0.000586964],"domain_scores_gemma":[0.993933,0.002206537,0.0005036318,0.001687628,0.001382641,0.0002865454],"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":[0.0001748098,0.00009949427,0.0003053485,0.00003003299,0.00004577321,0.0001098086,0.00009284027,0.9885433,0.00001585347,0.006173832,0.002731037,0.001677822],"study_design_scores_gemma":[0.0006658352,0.00007725231,0.0004901469,0.00003000189,0.00003122786,4.15504e-7,0.0006345942,0.6741056,0.00009924677,0.3210399,0.002507468,0.0003183485],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006209221,0.00003984617,0.9899802,0.0007572519,0.0009298949,0.001225282,0.0002190793,0.0003464696,0.0002927178],"genre_scores_gemma":[0.9664865,0.00008335764,0.008251585,0.00006834607,0.0002644711,0.00004076408,0.0003838691,0.00007857443,0.02434254],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9817287,"threshold_uncertainty_score":0.9998641,"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."}}