{"id":"W3209247505","doi":"10.1109/ccece53047.2021.9569056","title":"Reinforcement Learning Algorithms: An Overview and Classification","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":102,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Machine learning; Perspective (graphical); Field (mathematics); Robotics; Learning classifier system; Robot learning; Drone; Algorithm; Robot; Mobile robot","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","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0005862181,0.0003230063,0.0003434819,0.0001467531,0.0001819735,0.001356796,0.0009852876,0.0002660325,0.00009931416],"category_scores_gemma":[0.00009134864,0.000326245,0.00008636913,0.0002007118,0.00004628635,0.0006723184,0.002764982,0.0009020143,0.00003142363],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001244266,"about_ca_system_score_gemma":0.0002170264,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006428178,"about_ca_topic_score_gemma":0.00000429129,"domain_scores_codex":[0.9974543,0.0002082095,0.0005134997,0.0009173767,0.0005766639,0.000329957],"domain_scores_gemma":[0.9978943,0.00006663359,0.0003595493,0.001287709,0.0002161672,0.00017558],"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":[0.000001019512,0.0000173212,0.0002797198,0.0002036524,0.00004868585,0.00001023868,0.001088273,0.9079855,0.00007344946,0.05102589,0.00008990965,0.03917634],"study_design_scores_gemma":[0.0001410396,0.00009540773,0.001999413,0.0001647563,0.00001843671,0.000009767877,0.0001822271,0.9920535,0.00009622736,0.000271457,0.004588539,0.0003792331],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0007032534,0.0009402948,0.9881933,0.0004676047,0.0005433936,0.000300722,1.479649e-7,0.000418317,0.008432983],"genre_scores_gemma":[0.4178968,0.009124116,0.558037,0.001114704,0.0002921374,0.0001264878,0.0003964535,0.00007096139,0.01294133],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4301563,"threshold_uncertainty_score":0.9999189,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0971463287431973,"score_gpt":0.3273202482426542,"score_spread":0.2301739194994569,"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."}}