{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001496708,0.000255395,0.0005749363,0.0001451057,0.0004408793,0.0004638869,0.0009345219,0.00009000811,0.00007121963],"category_scores_gemma":[0.001121479,0.0002379566,0.0002325125,0.0003540954,0.00009844478,0.000725142,0.0003717806,0.0006543312,0.0000069832],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001017404,"about_ca_system_score_gemma":0.0001893441,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003091461,"about_ca_topic_score_gemma":5.30849e-7,"domain_scores_codex":[0.9968866,0.0002196884,0.001381477,0.0003887526,0.0006869277,0.0004365618],"domain_scores_gemma":[0.9962841,0.0005291884,0.001391056,0.0003976069,0.001169516,0.0002285197],"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":[0.00004434408,0.0001099476,0.0003579701,0.0003941269,0.000186255,0.0001172765,0.005021422,0.6928859,0.0005419934,0.2196639,0.0001721739,0.0805047],"study_design_scores_gemma":[0.001244134,0.003416746,0.0009807079,0.01524396,0.0002414937,0.0009587415,0.002580619,0.947329,0.005937934,0.005189305,0.01588368,0.0009936212],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0113102,0.004981975,0.9824118,0.0002736835,0.0006055859,0.0002510395,1.94462e-7,0.00005259657,0.0001128965],"genre_scores_gemma":[0.6577184,0.004768054,0.3338623,0.003046389,0.0003389932,0.00000462496,0.000006033205,0.00002717559,0.0002281197],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6485496,"threshold_uncertainty_score":0.9703589,"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."}}