{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008575333,0.0001504238,0.0001648714,0.0003916219,0.00007908745,0.0003292659,0.0003667196,0.00006903709,0.000004253252],"category_scores_gemma":[0.001878176,0.0001337627,0.00001013637,0.001018301,0.00006914234,0.001384715,0.0001765434,0.0003398868,0.00003031131],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001331039,"about_ca_system_score_gemma":0.0001864715,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001679221,"about_ca_topic_score_gemma":0.0001431985,"domain_scores_codex":[0.9984825,0.00006348037,0.0004873429,0.0002497318,0.0003948413,0.0003221391],"domain_scores_gemma":[0.9989749,0.0003967999,0.0001530295,0.0001682184,0.0002135283,0.00009356726],"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":[0.0000641548,0.00001015067,0.007968863,0.0000206626,0.000001513431,0.00001431907,0.009325266,0.8806962,0.000005200055,0.001563026,0.000006982968,0.1003237],"study_design_scores_gemma":[0.00008453534,0.0002094069,0.0002645901,0.0003148289,0.00000141454,0.00001054059,0.004695522,0.9903697,0.0003637572,0.003024287,0.0004668437,0.0001945665],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1094078,0.00005037044,0.8889863,0.0001252038,0.0001215959,0.0001827707,1.353916e-7,0.00007260119,0.001053202],"genre_scores_gemma":[0.9677154,0.00002071587,0.03212304,0.00007469608,0.0000216857,0.00001393381,0.000003606943,0.000005936438,0.00002100773],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8583075,"threshold_uncertainty_score":0.5454684,"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."}}