{"id":"W2136937392","doi":"10.1287/moor.1050.0148","title":"On the Empirical State-Action Frequencies in Markov Decision Processes Under General Policies","year":2005,"lang":"en","type":"article","venue":"Mathematics of Operations Research","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"National Science Foundation","keywords":"Polytope; Mathematics; Markov decision process; Markov chain; State (computer science); Element (criminal law); Action (physics); Limit (mathematics); Empirical research; Finite state; Markov process; Mathematical optimization; Mathematical economics; Combinatorics; Statistics; Algorithm; Mathematical analysis; Law","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":[0.001521223,0.0000974379,0.0001316309,0.0003734744,0.0002873355,0.0003575342,0.0008273652,0.0000463698,0.00005916406],"category_scores_gemma":[0.001459504,0.00006430689,0.00002667916,0.001057814,0.0001493979,0.0004203297,0.0002328607,0.0003249078,0.00008402902],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001577518,"about_ca_system_score_gemma":0.0002975253,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006723114,"about_ca_topic_score_gemma":0.0003100106,"domain_scores_codex":[0.9979848,0.0001593822,0.0003918225,0.0001834978,0.0009886674,0.0002918511],"domain_scores_gemma":[0.9974459,0.001434012,0.00003567263,0.0005692786,0.0004732678,0.00004191482],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003386227,0.0001135656,0.0000551319,0.00002564622,0.00000646389,4.841345e-7,0.004543518,0.8931477,0.0006337709,0.09974442,0.0006279575,0.001097978],"study_design_scores_gemma":[0.000129693,0.0001498061,0.0005286004,0.0000895233,0.000001199233,0.000003996066,0.0006847304,0.9797043,0.004961411,0.01346323,0.000194967,0.000088579],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4734502,0.00001710667,0.5207565,0.003880357,0.00002315515,0.0002612793,9.588447e-7,0.00002190877,0.001588562],"genre_scores_gemma":[0.8651178,0.00005998405,0.1330193,0.0001355698,0.00002846791,0.00005369675,0.000001711919,0.00001040591,0.001573091],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.3916676,"threshold_uncertainty_score":0.3447711,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3170072528469867,"score_gpt":0.4601731656936224,"score_spread":0.1431659128466358,"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."}}