{"id":"W4407949397","doi":"10.1109/cdc56724.2024.10886046","title":"Agent-state based policies in POMDPs: Beyond belief-state MDPs","year":2024,"lang":"en","type":"article","venue":"","topic":"Auction Theory and Applications","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Queen's University; University of Cyprus; Google; Adobe Systems","keywords":"Computer science; State (computer science); Artificial intelligence; 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":[0.00328154,0.001221569,0.001670065,0.0007701024,0.000595732,0.002263676,0.00161325,0.001679215,0.00330636],"category_scores_gemma":[0.01127747,0.0008361879,0.001006343,0.001265676,0.002116947,0.003801596,0.002017227,0.003364532,0.0003798069],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001729181,"about_ca_system_score_gemma":0.002847818,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004437884,"about_ca_topic_score_gemma":0.003886282,"domain_scores_codex":[0.998565,0.0006927231,0.00008888604,0.0002156647,0.0003252141,0.0001125085],"domain_scores_gemma":[0.9952088,0.003698218,0.000355825,0.000284039,0.0003042546,0.0001489001],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00003972048,0.0000344411,0.0003428644,0.0001494642,0.00003172815,0.00005392427,0.00009590185,0.8053705,0.000368754,0.1762695,0.0007065424,0.01653677],"study_design_scores_gemma":[0.00001434395,0.00002124538,0.00004783872,0.00002668986,0.000008075109,0.00001106763,0.00001763921,0.9021767,0.00023371,0.09604444,0.001391049,0.00000703534],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002987172,0.000334809,0.9940962,0.0002909609,0.00002878203,0.00004520883,0.00005123017,0.0001033142,0.002062367],"genre_scores_gemma":[0.5233474,0.002336677,0.4696777,0.0003261656,0.0001703786,0.0004630686,0.0002501863,0.0001396841,0.003288744],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004437884,"threshold_uncertainty_score":0.01735461,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07402671296376395,"score_gpt":0.3988489559587229,"score_spread":0.324822242994959,"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."}}