{"id":"W2159272820","doi":"10.1613/jair.3175","title":"Non-Deterministic Policies in Markovian Decision Processes","year":2011,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Research","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"National Institutes of Health; Duke-NUS Medical School; Natural Sciences and Engineering Research Council of Canada; McGill University","keywords":"Reinforcement learning; Computer science; Flexibility (engineering); Markov decision process; Set (abstract data type); Task (project management); Action selection; Markov process; Construct (python library); Process (computing); Action (physics); Decision problem; Artificial intelligence; Selection (genetic algorithm); Decision support system; Machine learning; Operations research; Algorithm; Mathematics; Engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.003230904,0.0008593774,0.00112294,0.0006196319,0.0006915096,0.001278236,0.00106405,0.001238697,0.002045144],"category_scores_gemma":[0.0132912,0.000675473,0.0008814179,0.0006859301,0.002329306,0.00176019,0.001157402,0.002101857,0.0002642169],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001848685,"about_ca_system_score_gemma":0.001819512,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007624727,"about_ca_topic_score_gemma":0.006490117,"domain_scores_codex":[0.998049,0.001092806,0.0001115666,0.0002829327,0.0002894703,0.0001742068],"domain_scores_gemma":[0.9877359,0.01064651,0.0007132209,0.0003309739,0.0003439755,0.0002295193],"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":[0.00007895296,0.00003583447,0.0007764323,0.00006011966,0.00002531848,0.00007138998,0.00009798063,0.9099399,0.0003118873,0.07802092,0.0002451852,0.01033607],"study_design_scores_gemma":[0.0000275102,0.00002145593,0.0001028969,0.00000970425,0.00000605131,0.00001241797,0.000009376994,0.9274821,0.0002354126,0.07175067,0.0003345647,0.000007914088],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.027043,0.0003180952,0.9706632,0.0003152957,0.0000303063,0.00005109408,0.00005723756,0.0002086234,0.001313167],"genre_scores_gemma":[0.7207313,0.0007359307,0.2758321,0.0001627689,0.00005768544,0.000321627,0.0001631919,0.00006268841,0.001932677],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007624727,"threshold_uncertainty_score":0.01708686,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.238712003270168,"score_gpt":0.4267161564176883,"score_spread":0.1880041531475203,"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."}}