{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001399931,0.0009437258,0.0009737325,0.0004544537,0.0003046159,0.001563727,0.0009574614,0.001274919,0.003119881],"category_scores_gemma":[0.003801634,0.0003151372,0.000703322,0.0007131114,0.001399439,0.001930118,0.001236951,0.003580568,0.0009198385],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001247241,"about_ca_system_score_gemma":0.001174415,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002324275,"about_ca_topic_score_gemma":0.001345862,"domain_scores_codex":[0.9992931,0.0002475855,0.00005158411,0.00009897534,0.0002666194,0.00004208751],"domain_scores_gemma":[0.998541,0.0009867213,0.00007622812,0.0001067273,0.0002351749,0.00005418549],"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":[0.00005377664,0.00006434749,0.0005992959,0.0006337202,0.00009741965,0.0001283381,0.0001548182,0.2102707,0.001310934,0.5906559,0.01018118,0.1858495],"study_design_scores_gemma":[0.00003988325,0.00007884664,0.0002632903,0.000206639,0.00003127864,0.00008864484,0.00003968255,0.4840948,0.0007483943,0.4430937,0.07128306,0.00003180243],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.003600271,0.05252477,0.9050002,0.006474872,0.001262374,0.00005029216,0.000090174,0.0003287872,0.03066828],"genre_scores_gemma":[0.5543076,0.1204806,0.2922224,0.002224885,0.004371632,0.0004484261,0.000374837,0.0002320211,0.02533764],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.003119881,"threshold_uncertainty_score":0.01043707,"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."}}