{"id":"W2138781282","doi":"10.1613/jair.3384","title":"Policy Invariance under Reward Transformations for General-Sum Stochastic Games","year":2011,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Research","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Royal Military College of Canada; Carleton University","funders":"","keywords":"Convergence (economics); Nash equilibrium; Mathematical economics; Property (philosophy); Markov chain; Computer science; Markov decision process; Mathematical optimization; Mathematics; Markov process; Economics; Machine learning","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":[0.001829808,0.0005914665,0.0006600526,0.0004161766,0.0004549478,0.001099607,0.0007873988,0.0007123808,0.002457483],"category_scores_gemma":[0.01095077,0.000299391,0.0007848144,0.0002842108,0.001822671,0.001585539,0.001881984,0.001628806,0.0003337],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008188389,"about_ca_system_score_gemma":0.0009253809,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001282388,"about_ca_topic_score_gemma":0.0006061392,"domain_scores_codex":[0.999061,0.0003708197,0.00004585486,0.0001481819,0.0002320433,0.0001420905],"domain_scores_gemma":[0.9968565,0.00201453,0.0003708869,0.0003008242,0.0002558627,0.000201465],"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":[0.000134989,0.00009390394,0.0005353341,0.00006977589,0.00004549818,0.0001922772,0.0002511871,0.5403879,0.00791953,0.4222916,0.0006125887,0.02746535],"study_design_scores_gemma":[0.00001595743,0.00005838953,0.0001102131,0.000006173868,0.000005541545,0.00002862384,0.00001673901,0.8426661,0.001168223,0.1555754,0.0003383801,0.00001023643],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05753302,0.00006830904,0.9351587,0.0002121273,0.00003600059,0.0000495071,0.00002587531,0.0001882497,0.006728244],"genre_scores_gemma":[0.9594554,0.0001363074,0.03681026,0.00009725608,0.00003060838,0.0001208564,0.00003966845,0.00009546015,0.003214194],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002457483,"threshold_uncertainty_score":0.009677052,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2839367873028663,"score_gpt":0.4274817902670979,"score_spread":0.1435450029642316,"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."}}