{"id":"W4384695760","doi":"10.22215/etd/2023-15579","title":"Learning of Deception in Adversarial Games with Hierarchical Multiobjective Reinforcement Learning","year":2023,"lang":"en","type":"dissertation","venue":"","topic":"Guidance and Control Systems","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"University of Guilan","keywords":"Deception; Reinforcement learning; Computer science; Adversarial system; Evasion (ethics); Differential (mechanical device); Artificial intelligence; Pursuit-evasion; Game theory; Psychology; Mathematical economics; Social psychology; Mathematics; Engineering","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":[0.0001743783,0.0002065038,0.0003712164,0.0002864923,0.00003287725,0.0000165989,0.00007579666,0.0002080094,0.00004554423],"category_scores_gemma":[0.00006242638,0.0001886236,0.00006988591,0.0002395336,0.0000107216,0.00008191814,0.000006890147,0.0006059397,0.00003788839],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001145383,"about_ca_system_score_gemma":0.00004383545,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005786101,"about_ca_topic_score_gemma":0.001767771,"domain_scores_codex":[0.9988706,0.00005144705,0.0003891175,0.0001917517,0.0002730575,0.0002240302],"domain_scores_gemma":[0.9996346,0.00007796467,0.0001058591,0.00008606951,0.00006331043,0.00003223699],"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":[0.000252977,0.000007094075,0.001948315,0.0002964053,0.0001080168,0.000005457085,0.006252937,0.9789615,0.003409982,0.00009795972,0.00002869244,0.008630643],"study_design_scores_gemma":[0.005191956,0.001024881,0.07992704,0.002685366,0.0001318375,0.000003039597,0.04942086,0.8552289,0.004135254,0.0000543289,0.001099093,0.001097427],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.96222,0.0001078595,0.004413237,0.000003561877,0.0006930122,0.0005722964,7.923998e-7,0.0004633014,0.03152599],"genre_scores_gemma":[0.98763,0.0000732331,0.00006443617,0.000001236723,0.0001084713,0.0001103288,0.0003072525,0.00006034103,0.0116447],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1237326,"threshold_uncertainty_score":0.7691846,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004880240954022649,"score_gpt":0.2181519611036813,"score_spread":0.2132717201496586,"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."}}