{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000413612,0.000271188,0.0003945705,0.000171749,0.0003741528,0.0005253076,0.001304829,0.0003053455,2.593616e-7],"category_scores_gemma":[0.00008317624,0.000319652,0.0001117627,0.00006127021,0.00009190467,0.0005130942,0.0007939286,0.0004211775,0.000003841885],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001165608,"about_ca_system_score_gemma":0.0001974396,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005732681,"about_ca_topic_score_gemma":0.000002865647,"domain_scores_codex":[0.9985144,0.00004138197,0.000225,0.0007961997,0.0001040624,0.0003189413],"domain_scores_gemma":[0.9980156,0.0002128401,0.0005273353,0.0009454853,0.000168129,0.000130612],"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":[0.00001396823,0.000007736996,0.002736289,0.0001061954,0.00008928406,0.000008247614,0.0002498298,0.9290528,0.00002296734,0.0676383,0.00004578866,0.00002855707],"study_design_scores_gemma":[0.001035502,0.00005723787,0.000713633,0.0001673965,0.0001038768,0.00000200767,0.00002030934,0.9951081,0.000005316246,0.002392301,0.00006197126,0.0003323465],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01113234,0.00004503631,0.9867875,0.0000521294,0.0003748973,0.0006474779,0.00003056821,0.0001562928,0.000773735],"genre_scores_gemma":[0.9897744,0.000009379835,0.008588139,0.00003632526,0.000127797,0.000003074013,0.00002615443,0.00001726941,0.001417461],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.978642,"threshold_uncertainty_score":0.9999256,"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."}}