{"id":"W4300362000","doi":"10.48550/arxiv.1712.02441","title":"A Novel Model for Arbitration between Planning and Habitual Control\\n Systems","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Action selection; Reinforcement learning; Internal model; Task (project management); Control (management); Action (physics); Artificial intelligence; Kinematics; A priori and a posteriori; Machine learning; Human–computer interaction; Engineering","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":[0.0004531952,0.000630943,0.0006576605,0.0002803654,0.0004858963,0.00139194,0.001992113,0.001222058,0.006778385],"category_scores_gemma":[0.001049888,0.0004211638,0.0007975096,0.0002955192,0.001142892,0.001904178,0.001471443,0.002067879,0.0008825677],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009342026,"about_ca_system_score_gemma":0.001349941,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003816382,"about_ca_topic_score_gemma":0.004005245,"domain_scores_codex":[0.9996754,0.00004855885,0.00001800041,0.0001242923,0.00007028699,0.00006342521],"domain_scores_gemma":[0.9996662,0.0001140773,0.00005106554,0.0000602522,0.00006204546,0.00004622133],"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":[0.0001512402,0.00008484148,0.0007359373,0.0001145823,0.0000671056,0.0002523813,0.0001829707,0.7699502,0.01018254,0.1847529,0.002659542,0.03086573],"study_design_scores_gemma":[0.00001833999,0.00003207098,0.00007863863,0.000003824262,0.00000889299,0.000028865,0.000005088715,0.974849,0.0005423479,0.0226841,0.001741763,0.000007005096],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02817413,0.0003081072,0.9528049,0.0007523543,0.000130075,0.00006743136,0.0002558846,0.001288085,0.01621896],"genre_scores_gemma":[0.883945,0.0003947646,0.08993759,0.0002422786,0.0001048474,0.0003385417,0.0002743515,0.0001587425,0.02460392],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006778385,"threshold_uncertainty_score":0.02267599,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1515338852204237,"score_gpt":0.2291927251955402,"score_spread":0.07765883997511644,"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."}}