{"id":"W2924816077","doi":"10.1613/jair.1.11418","title":"Modeling and Planning with Macro-Actions in Decentralized POMDPs","year":2019,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Research","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":62,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Office of Naval Research; National Institute of Mental Health; Multidisciplinary University Research Initiative; Air Force Office of Scientific Research; Defense Advanced Research Projects Agency; National Institutes of Health; National Science Foundation","keywords":"Computer science; Partially observable Markov decision process; Macro; Markov decision process; Exploit; Action (physics); Class (philosophy); Mathematical optimization; Artificial intelligence; Markov chain; Markov process; Markov model; Machine learning","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":[0.001855826,0.00008882488,0.0001891682,0.0005993817,0.000113843,0.000329079,0.0005844813,0.00005387374,0.00002527176],"category_scores_gemma":[0.0002294765,0.00007097164,0.0000334163,0.0007945243,0.00005758028,0.0006911795,0.0001494142,0.0008143232,0.00003485112],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001229156,"about_ca_system_score_gemma":0.0002361396,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004457747,"about_ca_topic_score_gemma":0.0000127904,"domain_scores_codex":[0.9978803,0.0001710247,0.0005053427,0.0001843807,0.000822575,0.0004363801],"domain_scores_gemma":[0.9987199,0.0003054283,0.0001126936,0.0002255002,0.0005032152,0.0001333042],"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":[0.00008028805,0.00003609843,0.002733328,0.00001419418,0.00001463857,0.00006393358,0.002157933,0.977469,0.001455872,0.009273256,0.00000569837,0.006695802],"study_design_scores_gemma":[0.00006661425,0.0003639403,0.0001800383,0.0001727971,0.000002049137,0.00007099236,0.001689575,0.9930395,0.00195218,0.002272105,0.0001059367,0.00008421562],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3627873,0.0001005013,0.6362987,0.0003076715,0.0001321058,0.0001061736,5.580359e-8,0.000009727021,0.0002577418],"genre_scores_gemma":[0.9662137,0.0001605808,0.03350972,0.00001623684,0.00005124862,0.000001379403,1.106683e-7,0.000007967464,0.00003903439],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6034264,"threshold_uncertainty_score":0.3537874,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2096420685101475,"score_gpt":0.4311779567163518,"score_spread":0.2215358882062043,"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."}}