{"id":"W2945054955","doi":"10.48550/arxiv.1905.10016","title":"A Micro-Objective Perspective of Reinforcement Learning","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Perspective (graphical); Reinforcement learning; Reinforcement; Computer science; Psychology; Artificial intelligence; Social psychology","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":[0.0003418895,0.0004165032,0.0005531952,0.0004718827,0.000136098,0.00009878967,0.002146734,0.0003277413,0.00004982789],"category_scores_gemma":[0.0001371039,0.0004980929,0.0003593292,0.0006446294,0.0001552857,0.000396494,0.00351442,0.001237096,0.0001796284],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008315761,"about_ca_system_score_gemma":0.0004703209,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003334157,"about_ca_topic_score_gemma":0.000004017805,"domain_scores_codex":[0.9975768,0.0002094788,0.000351376,0.00118246,0.000218121,0.0004617365],"domain_scores_gemma":[0.9967853,0.0001904196,0.0008334872,0.00143852,0.0006310262,0.0001211966],"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":[0.00003012545,0.00002491158,0.00193486,0.00008698015,0.0002043126,0.00003945844,0.00166872,0.8548553,0.0001147288,0.1409543,0.0000565752,0.0000297504],"study_design_scores_gemma":[0.0006459595,0.0002772103,0.0006089915,0.0002015673,0.00008327347,0.000003354511,0.001007889,0.9913439,0.0009053676,0.004155831,0.0002385035,0.000528202],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02232805,0.0000571604,0.9467029,0.00005049803,0.000602484,0.0005418347,0.000001864055,0.0002069965,0.02950822],"genre_scores_gemma":[0.9864228,0.0001394816,0.002602452,0.0000427107,0.0000438748,9.666978e-7,0.00001109132,0.0000269115,0.01070972],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9640948,"threshold_uncertainty_score":0.9997471,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04403034584286141,"score_gpt":0.1983845935839299,"score_spread":0.1543542477410685,"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."}}