{"id":"W2161717678","doi":"","title":"MDPs with Non-Deterministic Policies.","year":2009,"lang":"en","type":"article","venue":"PubMed","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Markov decision process; Flexibility (engineering); Context (archaeology); Mathematical optimization; Optimal decision; Integer (computer science); Markov process; Operations research; Artificial intelligence; Decision tree; Mathematics","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":[0.002361781,0.001316192,0.001285346,0.00064248,0.0005617105,0.001433163,0.001442058,0.001942636,0.004987882],"category_scores_gemma":[0.01036349,0.0007289769,0.001167946,0.0007701123,0.001749729,0.001921273,0.001619547,0.002236338,0.0005814895],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001590786,"about_ca_system_score_gemma":0.002190293,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004077429,"about_ca_topic_score_gemma":0.004389334,"domain_scores_codex":[0.9984139,0.000811486,0.0001063796,0.000250826,0.0002858732,0.0001314334],"domain_scores_gemma":[0.9929931,0.005591616,0.000690315,0.0002585457,0.0002658297,0.000200496],"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":[0.00007197137,0.00004701915,0.000449045,0.0001162266,0.00004080169,0.0001007063,0.00005232984,0.8981551,0.0002769154,0.08935973,0.000752188,0.01057787],"study_design_scores_gemma":[0.00003405883,0.00003491809,0.00007066307,0.00002009002,0.000014046,0.00002286181,0.00001511452,0.9420086,0.000261138,0.05590579,0.001604309,0.000008441938],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01450305,0.0007989463,0.9760562,0.0009202,0.0001008983,0.000200036,0.0002963056,0.0002298906,0.006894412],"genre_scores_gemma":[0.6244212,0.001285646,0.3630681,0.0004685075,0.0001149863,0.001151642,0.0005164633,0.00007327425,0.008900127],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004987882,"threshold_uncertainty_score":0.0166862,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01430034957822372,"score_gpt":0.2105713125744464,"score_spread":0.1962709629962227,"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."}}