{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001448457,0.001011675,0.0007614756,0.0005016118,0.0003078933,0.001903905,0.001416074,0.0009727547,0.003611935],"category_scores_gemma":[0.002685951,0.0003300813,0.0007233715,0.000560226,0.002039669,0.002684082,0.001073287,0.002553551,0.0004704426],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001626555,"about_ca_system_score_gemma":0.001098789,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002080925,"about_ca_topic_score_gemma":0.0021229,"domain_scores_codex":[0.999128,0.0003639802,0.00003757249,0.0001469417,0.0002553008,0.00006831828],"domain_scores_gemma":[0.9987112,0.0006851837,0.0001754789,0.0001437218,0.0001816726,0.0001027223],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00002175088,0.0000341919,0.0003061879,0.000115938,0.00004851406,0.00006367955,0.00008954677,0.2616112,0.0009731234,0.7176154,0.001053879,0.01806661],"study_design_scores_gemma":[0.00001641119,0.00005536199,0.0001700047,0.0000391655,0.00001873128,0.00003786819,0.00003147514,0.5857909,0.0006147266,0.4073258,0.005883472,0.00001606207],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00365193,0.0007814257,0.9836236,0.00100832,0.00007174565,0.00002786051,0.00006633844,0.00007397567,0.01069471],"genre_scores_gemma":[0.6546695,0.002269781,0.3285074,0.0005758462,0.0004181383,0.0002790145,0.0001304594,0.000131528,0.01301834],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003611935,"threshold_uncertainty_score":0.01208311,"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."}}