{"id":"W2608848790","doi":"10.48550/arxiv.1704.07511","title":"Scalable Planning with Tensorflow for Hybrid Nonlinear Domains","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Scalability; Computer science; Mathematical optimization; Nonlinear system; Gradient descent; Deep learning; Nonlinear programming; Optimization problem; Artificial intelligence; Artificial neural network; 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":[0.0002933073,0.0003502829,0.000398212,0.0001904491,0.0006226895,0.0003837719,0.002378094,0.0001526606,0.000007854323],"category_scores_gemma":[0.00005856072,0.0003371717,0.0001853515,0.0001350077,0.000120882,0.0003320143,0.001227973,0.0006783708,0.00003663042],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008356046,"about_ca_system_score_gemma":0.0002304954,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001404259,"about_ca_topic_score_gemma":0.000009380652,"domain_scores_codex":[0.9980075,0.00006462637,0.0001423285,0.001196381,0.0001098547,0.000479311],"domain_scores_gemma":[0.9975125,0.000121646,0.0003462433,0.001647491,0.0001839559,0.0001882294],"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":[0.0001270876,0.0001517406,0.008921517,0.0002359125,0.0002533094,0.001457855,0.0002846417,0.9602927,0.0000150103,0.02230278,0.001584207,0.004373209],"study_design_scores_gemma":[0.0008781264,0.0001426523,0.0004932344,0.0002219343,0.00005839061,0.0000218621,0.0000191252,0.9824992,0.00009476282,0.007380781,0.007681953,0.0005080179],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1139975,0.00004237517,0.8816279,0.000200461,0.0004718805,0.0003255562,0.00003851414,0.0003254214,0.002970356],"genre_scores_gemma":[0.9057342,0.00002343753,0.08413807,0.00009188631,0.0003303601,0.000002884724,0.00004735522,0.00003793807,0.009593849],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7974898,"threshold_uncertainty_score":0.999908,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05397850387346422,"score_gpt":0.2120377913914784,"score_spread":0.1580592875180142,"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."}}