{"id":"W4390636078","doi":"10.2139/ssrn.4685924","title":"Learning Deception and Agent Assignment Using a Hierarchical Reinforcement Learning","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Deception detection and forensic psychology","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Carleton University","funders":"","keywords":"Deception; Reinforcement learning; Reinforcement; Computer science; Artificial intelligence; Psychology; Social psychology","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":[0.002628771,0.0007059459,0.001255041,0.0006106368,0.0006877941,0.001025581,0.002302786,0.001978743,0.003863356],"category_scores_gemma":[0.01484762,0.0006885012,0.0006709766,0.0004129683,0.001674909,0.002443915,0.002047622,0.002782332,0.0003734542],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00130431,"about_ca_system_score_gemma":0.001496634,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005226865,"about_ca_topic_score_gemma":0.004505085,"domain_scores_codex":[0.9989247,0.0004601365,0.00005183602,0.0002543196,0.0001655756,0.0001435413],"domain_scores_gemma":[0.9902982,0.007107359,0.0007404907,0.0006609966,0.0006789172,0.0005140179],"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":[0.0003619258,0.0003554902,0.003235553,0.00007570722,0.0001026498,0.000102441,0.0001861349,0.9130372,0.001582216,0.02538447,0.001091131,0.05448509],"study_design_scores_gemma":[0.0000190876,0.00004001709,0.0001237965,0.000002749777,0.000008100897,0.000007429272,0.000005013965,0.9929513,0.0001702759,0.00661233,0.00005577201,0.000003994006],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1654077,0.0001620352,0.8292531,0.0007899558,0.00009138222,0.0001809318,0.00005610632,0.0004385407,0.003620143],"genre_scores_gemma":[0.9411332,0.00006211025,0.05595126,0.0001104449,0.00004185411,0.0001071912,0.00003751502,0.00002419506,0.002532302],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005226865,"threshold_uncertainty_score":0.01390243,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02596530119975256,"score_gpt":0.3317513507294316,"score_spread":0.3057860495296791,"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."}}