{"id":"W2336187745","doi":"10.14288/1.0135671","title":"Reinforcement learning in non-stationary games","year":2015,"lang":"en","type":"article","venue":"Open Collections","topic":"Game Theory and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Reinforcement; Reinforcement learning; Computer science; Psychology; Cognitive psychology; Artificial intelligence; 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":[0.002153639,0.001166815,0.001551445,0.0005105727,0.0004669418,0.001444342,0.001200296,0.001439199,0.002624442],"category_scores_gemma":[0.008222006,0.0004302871,0.0007163682,0.0004517763,0.002272747,0.001148367,0.001144063,0.001992022,0.0003003645],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002000212,"about_ca_system_score_gemma":0.001679311,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004815133,"about_ca_topic_score_gemma":0.002822711,"domain_scores_codex":[0.9985574,0.0007740356,0.00006298903,0.0002204426,0.0002229669,0.0001622572],"domain_scores_gemma":[0.9931497,0.005594051,0.0004845873,0.0001404597,0.0004113504,0.0002199825],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00005101395,0.00004929202,0.0005678974,0.00009323363,0.00004160815,0.00008372917,0.00009719007,0.8546581,0.0003783034,0.134666,0.0006921577,0.008621451],"study_design_scores_gemma":[0.00001674645,0.00002042,0.00005402536,0.000006469057,0.000003964212,0.00000612339,0.000009612924,0.9626344,0.00005612324,0.0368609,0.0003270881,0.000004236471],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03310476,0.0005827295,0.9558094,0.0008001587,0.00009701649,0.0001046605,0.00006801426,0.0001362466,0.009296976],"genre_scores_gemma":[0.9348658,0.0007041949,0.05609257,0.000236525,0.0001299296,0.0004438787,0.00008906303,0.00003850221,0.007399446],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004815133,"threshold_uncertainty_score":0.0145126,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1305304030307569,"score_gpt":0.405381822823183,"score_spread":0.2748514197924262,"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."}}