{"id":"W2272644799","doi":"10.1609/aaai.v29i1.9659","title":"Information Gathering and Reward Exploitation of Subgoals for POMDPs","year":2015,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds Québécois de la Recherche sur la Nature et les Technologies","keywords":"Partially observable Markov decision process; Computer science; Benchmark (surveying); Solver; Time horizon; Markov decision process; Space (punctuation); State (computer science); Artificial intelligence; Machine learning; Markov chain; Markov process; Markov model; Mathematical optimization; Mathematics; Algorithm","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006553527,0.0001108877,0.0001599434,0.0001079911,0.00006630219,0.0001476461,0.0007156919,0.00005201258,0.000002413109],"category_scores_gemma":[0.0008787372,0.00008853296,0.0000451489,0.0002658308,0.00009424186,0.001025294,0.0001850628,0.00009070899,0.000008641525],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003061865,"about_ca_system_score_gemma":0.00007329838,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001226257,"about_ca_topic_score_gemma":6.792297e-7,"domain_scores_codex":[0.9988673,0.000008127411,0.0004769967,0.0001341648,0.0003504718,0.0001628902],"domain_scores_gemma":[0.9982347,0.00008725259,0.0004908295,0.0001544365,0.0009733203,0.00005948461],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005606384,0.00002686359,0.0003173237,0.0001154054,0.0000122423,1.827589e-8,0.01207865,0.005980539,0.006743193,0.9480742,0.00008898383,0.02650649],"study_design_scores_gemma":[0.00007778766,0.0005414879,0.0001731761,0.0002122522,0.00001329692,0.000001983167,0.003100561,0.5186226,0.376112,0.1006856,0.0002798199,0.0001794471],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1385311,0.0000112909,0.8551894,0.00118362,0.0003053932,0.0005758414,0.000001781466,0.00007557668,0.004125992],"genre_scores_gemma":[0.97769,0.00001556285,0.02214184,0.00006088208,0.00001855465,0.00002090767,4.386167e-7,0.000004866726,0.00004689153],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8473886,"threshold_uncertainty_score":0.3610269,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1196532880799096,"score_gpt":0.3033813658153713,"score_spread":0.1837280777354617,"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."}}