{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001995878,0.001116921,0.001108977,0.0006019995,0.0005689632,0.0007018175,0.001309035,0.0009490335,0.001850171],"category_scores_gemma":[0.005780852,0.0005621527,0.0009824305,0.0004103233,0.001356745,0.001392633,0.001886062,0.001789665,0.0002566521],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009202149,"about_ca_system_score_gemma":0.001846596,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00274827,"about_ca_topic_score_gemma":0.003234598,"domain_scores_codex":[0.9990593,0.0003856238,0.00005812917,0.0001876082,0.0001994991,0.0001098927],"domain_scores_gemma":[0.9974058,0.001892388,0.0002707098,0.0001670195,0.000135228,0.0001288498],"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":[0.000128042,0.00008767997,0.0009535943,0.0001708848,0.00004493605,0.0001100206,0.00016369,0.929772,0.002308069,0.02079069,0.0007544727,0.04471598],"study_design_scores_gemma":[0.00002969819,0.0000402851,0.00007960468,0.00001179142,0.000009376249,0.00001375709,0.00001548077,0.9870129,0.0008844556,0.01142725,0.0004696085,0.00000590967],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03647704,0.0002564852,0.9598259,0.000269219,0.00002512509,0.000164115,0.00008704312,0.0008003504,0.002094605],"genre_scores_gemma":[0.6215093,0.0002218666,0.3763329,0.0001436393,0.00002485948,0.0003691006,0.0002126113,0.000146412,0.001039306],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00274827,"threshold_uncertainty_score":0.01055533,"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."}}