{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001276598,0.0007442669,0.0007625017,0.0003766993,0.0005203456,0.001172549,0.001029084,0.0008020538,0.001733584],"category_scores_gemma":[0.002943004,0.0005720668,0.0007816371,0.0005141821,0.001203703,0.001281365,0.001346051,0.001518225,0.0002022407],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00107358,"about_ca_system_score_gemma":0.001382387,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005792742,"about_ca_topic_score_gemma":0.007364449,"domain_scores_codex":[0.9993474,0.0002297257,0.00004449004,0.0001445738,0.0001482253,0.00008562833],"domain_scores_gemma":[0.9986859,0.0008383844,0.0001790786,0.0001175889,0.0001025047,0.00007652195],"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":[0.00002298945,0.00001256175,0.0002919135,0.00003246828,0.000009994695,0.00004707754,0.00003734376,0.9762113,0.0003726581,0.01738191,0.0001785192,0.005401298],"study_design_scores_gemma":[0.000009949988,0.0000110279,0.00006496305,0.000004597137,0.000003593588,0.000007650508,0.00001084934,0.9849852,0.0002376653,0.01413368,0.0005276392,0.000003198655],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0201081,0.0001562998,0.9770823,0.0001527518,0.00002129399,0.00005564762,0.0001235186,0.0002862556,0.002013892],"genre_scores_gemma":[0.6724612,0.0004029033,0.3242426,0.00009323659,0.00003501041,0.0003466093,0.0002713357,0.00007795761,0.002069161],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005792742,"threshold_uncertainty_score":0.01151806,"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."}}