{"id":"W4210401180","doi":"10.1371/journal.pone.0262249","title":"Breaking the bonds of reinforcement: Effects of trial outcome, rule consistency and rule complexity against exploitable and unexploitable opponents","year":2022,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Experimental Behavioral Economics Studies","field":"Social Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University; University of Alberta","funders":"Osk. Huttusen säätiö; University of Sussex","keywords":"Reinforcement learning; Reinforcement; Exploit; Outcome (game theory); Consistency (knowledge bases); Computer science; Game theory; Simple (philosophy); Adversary; Artificial intelligence; Psychology; Mathematical economics; Social psychology; Computer security; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005473693,0.0006829896,0.001033169,0.0005015846,0.0003288024,0.001813347,0.001038638,0.0009603391,0.002901396],"category_scores_gemma":[0.05770067,0.0005116272,0.0004244413,0.0002384264,0.001339224,0.001750112,0.00132063,0.001917658,0.0002850961],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005926972,"about_ca_system_score_gemma":0.0005473525,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008172188,"about_ca_topic_score_gemma":0.001089244,"domain_scores_codex":[0.9973028,0.0008472004,0.0004017336,0.0006449382,0.0005818011,0.0002215501],"domain_scores_gemma":[0.9113815,0.06506416,0.01241164,0.006565849,0.001183245,0.003393614],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.1509869,0.0272955,0.2188034,0.00136562,0.003158337,0.0008713962,0.002503688,0.104828,0.3350557,0.007364728,0.001014866,0.1467517],"study_design_scores_gemma":[0.006924098,0.0872062,0.4850318,0.0002064672,0.001714276,0.0007504388,0.0009796059,0.2823837,0.09595709,0.03594562,0.002465219,0.000435591],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9986286,0.00003455584,0.0006083226,0.00003330058,0.000008436376,0.00003569127,0.00002759739,0.00001101992,0.0006125466],"genre_scores_gemma":[0.9975128,0.00003209364,0.001708157,0.00004437217,0.00001019893,0.00007268771,0.00007499522,0.00001791694,0.0005268228],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005473693,"threshold_uncertainty_score":0.02894795,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1241823366200126,"score_gpt":0.3071874736431783,"score_spread":0.1830051370231658,"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."}}