{"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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001888803,0.000064211,0.0001247874,0.0001518795,0.0008807361,0.001045248,0.0005722168,0.00003055132,0.001453505],"category_scores_gemma":[0.001056833,0.00005567124,0.00002933655,0.002442734,0.00004430215,0.0004018693,0.0002147473,0.0001312766,0.0004964347],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007848013,"about_ca_system_score_gemma":0.0002239435,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001120217,"about_ca_topic_score_gemma":0.0007483798,"domain_scores_codex":[0.9987704,0.0001410663,0.0003403641,0.0002411583,0.000372552,0.0001344329],"domain_scores_gemma":[0.9988682,0.0004422544,0.00009780219,0.0002804588,0.0002106552,0.0001005931],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00005540965,0.0001105939,0.0008587671,5.621463e-7,0.000007800892,0.000002813448,0.001805563,0.149952,0.00006900089,0.006298091,0.8350417,0.005797695],"study_design_scores_gemma":[0.001052155,0.0001512008,0.002583653,0.00001259702,0.000005992956,0.00001225651,0.01156061,0.02416927,0.0002423503,0.2115556,0.7484639,0.0001904383],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.006059663,0.000008804823,0.01475239,0.001061958,0.0001369983,0.0004949637,0.000003178626,0.00002501523,0.977457],"genre_scores_gemma":[0.4952174,0.000002154373,0.0007203607,0.0001001982,0.00001875393,0.0001885277,0.000004766016,0.000003714202,0.5037442],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.4891577,"threshold_uncertainty_score":0.9999918,"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."}}