{"id":"W3038500004","doi":"10.1007/s12652-021-03489-y","title":"A conceptual framework for externally-influenced agents: an assisted reinforcement learning review","year":2021,"lang":"en","type":"article","venue":"Journal of Ambient Intelligence and Humanized Computing","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Reinforcement; Conceptual framework; Process (computing); Heuristic; Interoperability","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":[0.003609672,0.001489654,0.001380758,0.001452895,0.0005405489,0.0038969,0.004910993,0.003579432,0.002362933],"category_scores_gemma":[0.004700192,0.0005870622,0.0009464438,0.001944141,0.007223248,0.00458376,0.00180519,0.005024124,0.0008551975],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003794418,"about_ca_system_score_gemma":0.003400104,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003901859,"about_ca_topic_score_gemma":0.002716454,"domain_scores_codex":[0.9985251,0.0005744262,0.0001104294,0.0003058037,0.0003969973,0.00008721607],"domain_scores_gemma":[0.9966257,0.002199419,0.0002318722,0.0002052097,0.0005904983,0.0001473334],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002981732,0.00009731337,0.000296646,0.00179754,0.00007558324,0.00006951451,0.0002469929,0.04065829,0.0004522047,0.8179275,0.00365715,0.1346914],"study_design_scores_gemma":[0.00005211981,0.0002469305,0.0005454288,0.002594601,0.0001279299,0.0002914418,0.0003141598,0.1086936,0.000974257,0.6732743,0.212773,0.0001122396],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.003266661,0.4682231,0.4806414,0.01195148,0.001542732,0.00009337827,0.00007208843,0.0001952815,0.03401396],"genre_scores_gemma":[0.3063149,0.4874223,0.1896856,0.003914848,0.002560118,0.0004459998,0.0001581435,0.0001429574,0.009354985],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.004910993,"threshold_uncertainty_score":0.02753055,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07417532899007453,"score_gpt":0.3493026668596729,"score_spread":0.2751273378695984,"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."}}