{"id":"W4381733153","doi":"10.3233/faia230098","title":"Reinforcement Learning Requires Human-in-the-Loop Framing and Approaches","year":2023,"lang":"en","type":"book-chapter","venue":"Frontiers in artificial intelligence and applications","topic":"Mental Health Research Topics","field":"Psychology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Human-in-the-loop; Framing (construction); Computer science; Markov decision process; Set (abstract data type); Artificial intelligence; Markov process; Engineering; Mathematics","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":[0.0007565055,0.0001893497,0.000249861,0.0003341354,0.0003073842,0.00006593767,0.0002644721,0.0002436788,0.00009658213],"category_scores_gemma":[0.00002235136,0.0001797959,0.00003424073,0.0001382793,0.0003558194,0.00004686439,0.0001006871,0.0008359739,0.0001060959],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007054265,"about_ca_system_score_gemma":0.00002698436,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001554969,"about_ca_topic_score_gemma":0.0002118224,"domain_scores_codex":[0.9983287,0.00006301565,0.0005592442,0.0004775673,0.0002233775,0.0003480817],"domain_scores_gemma":[0.9992856,0.0001606208,0.0001341918,0.0003258053,0.00001909019,0.00007466735],"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":[0.00001306711,0.00002372249,0.0002344895,0.00008030783,0.00001355339,0.000008079186,0.001912481,0.00008795731,0.000002364362,0.6603031,0.0006176547,0.3367032],"study_design_scores_gemma":[0.0001018342,0.0002611896,0.0004632409,0.0003563429,0.00003928967,0.000009269648,0.02159664,0.004050638,0.00005501637,0.7656468,0.2068024,0.0006173726],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.001334772,0.007172172,0.1503427,0.002415885,0.0007877413,0.006222554,0.00002712409,0.0001614865,0.8315355],"genre_scores_gemma":[0.1835707,0.006487328,0.002068189,0.0005192723,0.001210289,0.004371341,0.0003711419,0.00018624,0.8012155],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.3360858,"threshold_uncertainty_score":0.7331864,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2781771810200347,"score_gpt":0.4138547181675101,"score_spread":0.1356775371474753,"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."}}