{"id":"W7143646775","doi":"10.71465/ajainn17","title":"Advances in Reinforcement Learning for Autonomous Systems","year":2020,"lang":"","type":"article","venue":"American Journal of Artificial Intelligence and Neural Networks","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Reinforcement learning; Autonomous system (mathematics); Reinforcement; Autonomous learning; Autonomous agent","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":[0.0009389399,0.0004020775,0.0009615132,0.0002277212,0.000264244,0.0005684917,0.0008923277,0.00009589319,0.00001103209],"category_scores_gemma":[0.0003774053,0.0003806005,0.0001964019,0.001073746,0.0004979461,0.001234254,0.0002257027,0.001173601,0.000003650937],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009039883,"about_ca_system_score_gemma":0.0001299733,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003091798,"about_ca_topic_score_gemma":0.000003876822,"domain_scores_codex":[0.9956965,0.0003048798,0.002218846,0.0004917572,0.000492499,0.0007955246],"domain_scores_gemma":[0.9960049,0.0007265638,0.002256725,0.0001995663,0.0003468104,0.0004654246],"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":[0.0002859116,0.00001483211,0.000247598,0.00003616278,0.00002121185,0.00003156723,0.001403789,0.5997745,0.00001521321,0.001572889,0.000009731398,0.3965865],"study_design_scores_gemma":[0.0001093563,0.009958771,0.00001858364,0.0002506504,0.00004389855,0.0000603117,0.002666212,0.9846998,0.00008635319,0.00008198508,0.001651697,0.0003723838],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004769635,0.005111705,0.98633,0.001737496,0.00151556,0.0004491605,3.046847e-7,0.000023114,0.00006297437],"genre_scores_gemma":[0.9886189,0.007817019,0.001808256,0.0006453944,0.001050003,0.000007649704,0.000001252149,0.00002861474,0.00002295415],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9845218,"threshold_uncertainty_score":0.9998646,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04069044415421257,"score_gpt":0.291021302767235,"score_spread":0.2503308586130225,"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."}}