{"id":"W2406813038","doi":"","title":"Learning and planning with timing information in Markov decision processes","year":2015,"lang":"en","type":"article","venue":"Uncertainty in Artificial Intelligence","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; Representation (politics); Artificial intelligence; Machine learning; Markov chain; Markov process; Set (abstract data type); State (computer science); Robot; Duration (music); Algorithm; 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":[0.002363086,0.0007817065,0.001115172,0.00056274,0.0005331376,0.00111546,0.001204165,0.001305346,0.001628481],"category_scores_gemma":[0.009541492,0.0006235167,0.0008021451,0.0008138585,0.002051098,0.002978705,0.001339638,0.001574499,0.0001769299],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001376833,"about_ca_system_score_gemma":0.001251975,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006218723,"about_ca_topic_score_gemma":0.004011709,"domain_scores_codex":[0.9988616,0.0005912927,0.00005668914,0.0002165679,0.0001565185,0.0001174919],"domain_scores_gemma":[0.9933261,0.005645429,0.0004212467,0.0002202384,0.0002130069,0.0001740321],"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":[0.00008156322,0.00002095852,0.0002885111,0.00002708643,0.00001504891,0.00004895794,0.00004490525,0.9554352,0.000341535,0.0361472,0.0001047474,0.007444264],"study_design_scores_gemma":[0.00001196453,0.00001170616,0.0000320744,0.000002804264,0.000002897046,0.000004453295,0.00000383819,0.9674666,0.000173841,0.032222,0.00006387462,0.000004009566],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08509644,0.0002491462,0.9126031,0.0004296591,0.00002643832,0.00002866551,0.00007334019,0.0001810184,0.0013123],"genre_scores_gemma":[0.9035395,0.0002567582,0.09464844,0.00007725677,0.00003789809,0.0001027452,0.0001404814,0.00004696741,0.001149959],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006218723,"threshold_uncertainty_score":0.01249737,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05173460047726749,"score_gpt":0.3098116824769045,"score_spread":0.258077081999637,"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."}}