{"id":"W3111857876","doi":"10.1609/aaai.v35i6.16702","title":"Hindsight and Sequential Rationality of Correlated Play","year":2021,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; University of Alberta","funders":"Division of Civil, Mechanical and Manufacturing Innovation; Alberta Machine Intelligence Institute; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research; National Science Foundation","keywords":"Hindsight bias; Rationality; Mathematical economics; Computer science; Counterfactual thinking; Regret; Bounded rationality; Fictitious play; Game theory; Artificial intelligence; Mathematics; Epistemology; Machine learning; Psychology; Cognitive psychology; Social psychology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0005518949,0.0002216549,0.0003387361,0.0001042475,0.0001819497,0.0001973683,0.001305284,0.0001346455,0.0001666891],"category_scores_gemma":[0.0008644135,0.0001789353,0.0001286444,0.0008044226,0.0005901682,0.0005102159,0.0006045875,0.000315062,0.00003583961],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003737089,"about_ca_system_score_gemma":0.0002589227,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005369676,"about_ca_topic_score_gemma":0.0000250052,"domain_scores_codex":[0.9976421,0.00004574311,0.0008342406,0.0005651655,0.000621594,0.0002911472],"domain_scores_gemma":[0.9973163,0.0002143366,0.000526108,0.0003760864,0.001469984,0.00009718008],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003191981,0.0001412379,0.0006645146,0.00003002649,0.00002294711,0.000001449827,0.001585136,0.00007534167,0.1321512,0.8437922,0.00007529101,0.02142872],"study_design_scores_gemma":[0.00001528805,0.00006590073,0.0004350173,0.0001295927,0.00001283454,0.00001215825,0.000377779,0.03098882,0.7675764,0.2001772,0.00005860527,0.0001504022],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8850184,0.0001720819,0.09026676,0.007207516,0.001352825,0.0005572335,0.000021032,0.000133354,0.01527077],"genre_scores_gemma":[0.9954897,0.00005727035,0.003969042,0.0001336918,0.00004841315,0.00001093607,9.137906e-7,0.00000992653,0.0002800814],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.643615,"threshold_uncertainty_score":0.7296771,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08312385965456567,"score_gpt":0.3069914782112599,"score_spread":0.2238676185566942,"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."}}