{"id":"W2101984404","doi":"","title":"VDCBPI: an Approximate Scalable Algorithm for Large POMDPs","year":2004,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":65,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Scalability; Markov decision process; Curse of dimensionality; Computer science; Bounded function; Markov process; Mathematical optimization; Observable; Algorithm; Theoretical computer science; Mathematics; Artificial intelligence","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":[0.001244114,0.001102792,0.00129854,0.0008297948,0.0007584221,0.00112731,0.002624706,0.001384462,0.005783505],"category_scores_gemma":[0.004602226,0.0007252821,0.0006938454,0.0008792078,0.0008230268,0.001664762,0.00272552,0.002338673,0.001093377],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001351786,"about_ca_system_score_gemma":0.004133764,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007495007,"about_ca_topic_score_gemma":0.007877448,"domain_scores_codex":[0.9993954,0.0001111636,0.00003553686,0.0001403306,0.0002324758,0.00008516131],"domain_scores_gemma":[0.9985776,0.0007818908,0.00008821865,0.0002673665,0.0001896495,0.00009532982],"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":[0.0002065018,0.0001249364,0.0008232992,0.0002079652,0.00006696322,0.0001033639,0.00007376865,0.5949464,0.002480134,0.02721192,0.009299424,0.3644554],"study_design_scores_gemma":[0.00004089897,0.00001457931,0.00003166081,0.000006885818,0.000004012259,0.00001645462,0.000006494576,0.9902959,0.0006071505,0.007825111,0.001146489,0.000004294762],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004228387,0.0001650574,0.9900107,0.0001804993,0.00006939404,0.0001309238,0.0001089647,0.003092692,0.002013458],"genre_scores_gemma":[0.1603163,0.0001764436,0.8359768,0.0002235244,0.00004580975,0.0005815393,0.0004691095,0.0003972897,0.001813123],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007495007,"threshold_uncertainty_score":0.01934773,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01861896870123979,"score_gpt":0.2662121577549219,"score_spread":0.2475931890536821,"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."}}