{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003324919,0.0001389547,0.0002429885,0.0009171236,0.0003451514,0.0002932424,0.001680133,0.00009809709,0.00005387111],"category_scores_gemma":[0.001173627,0.0001206058,0.0001719935,0.001192625,0.0002267236,0.001041023,0.000133684,0.0006488269,0.00009125513],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001866358,"about_ca_system_score_gemma":0.0008962331,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007209532,"about_ca_topic_score_gemma":0.00001491249,"domain_scores_codex":[0.9969788,0.0002156846,0.0009393626,0.0002103869,0.000995241,0.0006605939],"domain_scores_gemma":[0.9969935,0.0005628444,0.0002893515,0.0004202697,0.001489082,0.0002449219],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007928378,0.00009165869,0.000007100266,0.00002216503,0.00004393371,0.000007408757,0.004234954,0.289068,0.001145997,0.6682715,0.0003304004,0.03669766],"study_design_scores_gemma":[0.00008218078,0.001096686,0.0001169862,0.0001033333,0.000009370399,0.00006430957,0.0009837464,0.5628976,0.02091018,0.4129621,0.0005621315,0.0002112907],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001713703,0.00005910573,0.9933514,0.002913395,0.0004061223,0.0003274491,0.000001481003,0.00002454387,0.001202828],"genre_scores_gemma":[0.8490356,0.0001655674,0.1495097,0.0001641496,0.0006205224,0.00002147887,8.491455e-7,0.00002088812,0.0004611975],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8473219,"threshold_uncertainty_score":0.4918161,"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."}}