{"id":"W4385965908","doi":"10.48550/arxiv.2308.08427","title":"Eliciting Risk Aversion with Inverse Reinforcement Learning via Interactive Questioning","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Auction Theory and Applications","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Hong Kong University of Science and Technology; University of Toronto","keywords":"Risk aversion (psychology); Computer science; Reinforcement learning; Set (abstract data type); Function (biology); Distortion (music); Discounting; Econometrics; Economics; Mathematical economics; Artificial intelligence; Expected utility hypothesis; Finance","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00938061,0.001266952,0.0013704,0.0005761385,0.0003510892,0.001463026,0.002579932,0.001850568,0.003705879],"category_scores_gemma":[0.0431693,0.0006700375,0.000802932,0.0004582153,0.002047044,0.0029556,0.002046767,0.002337479,0.0005002329],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001000911,"about_ca_system_score_gemma":0.0008850822,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001223948,"about_ca_topic_score_gemma":0.0008205735,"domain_scores_codex":[0.9924828,0.005260142,0.0002040813,0.001154137,0.0006348037,0.0002640373],"domain_scores_gemma":[0.9572114,0.03474303,0.003035412,0.003273931,0.00109217,0.0006441503],"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":[0.001606593,0.001986446,0.01371095,0.0004280657,0.0003171951,0.0003497166,0.001662663,0.6566139,0.0147156,0.09826409,0.00147413,0.2088706],"study_design_scores_gemma":[0.0001009262,0.0002857153,0.001254187,0.00001956878,0.00002328784,0.00005352686,0.00007020155,0.9476268,0.002322979,0.04746739,0.0007443537,0.00003110467],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08212391,0.00009513415,0.9145989,0.0003406097,0.00001208219,0.0002074682,0.00005558093,0.0004046519,0.002161603],"genre_scores_gemma":[0.8215379,0.00004883519,0.1769836,0.000139576,0.00001431922,0.0002829894,0.00006325098,0.00002935407,0.000900235],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00938061,"threshold_uncertainty_score":0.04961002,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1472760959803459,"score_gpt":0.2686159908612994,"score_spread":0.1213398948809535,"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."}}