{"id":"W4200372371","doi":"10.1002/cpe.6743","title":"Scalable grid‐based approximation algorithms for partially observable Markov decision processes","year":2021,"lang":"en","type":"article","venue":"Concurrency and Computation Practice and Experience","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Partially observable Markov decision process; Computer science; Markov decision process; Scalability; Observable; Mathematical optimization; Implementation; Grid; Markov process; Process (computing); Focus (optics); Algorithm; Markov chain; Markov model; Machine learning; Mathematics","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":[0.001651692,0.000707464,0.001491592,0.0005652175,0.0006141212,0.001002046,0.001607456,0.0008401305,0.003609907],"category_scores_gemma":[0.005342954,0.0005073301,0.0006205681,0.000857225,0.0009131033,0.001146764,0.001659163,0.00156512,0.0003538722],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001696145,"about_ca_system_score_gemma":0.002115288,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01517625,"about_ca_topic_score_gemma":0.01313475,"domain_scores_codex":[0.9993342,0.0002565235,0.00003926563,0.0001128999,0.0001538727,0.0001031074],"domain_scores_gemma":[0.9962585,0.002829586,0.0002749763,0.0002623467,0.0002311154,0.0001435695],"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":[0.00004474174,0.00002204116,0.0003663453,0.000027252,0.00001329168,0.00001737583,0.00002312706,0.9825925,0.0001209023,0.007376273,0.0003430196,0.009053187],"study_design_scores_gemma":[0.000005805095,0.000003063782,0.00001424741,0.000001827372,8.431728e-7,0.000001539048,0.000002931164,0.9970799,0.00002402916,0.002811068,0.00005406598,6.537211e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03536696,0.00046718,0.9598309,0.000335883,0.00005321293,0.000069273,0.0001267172,0.0008190753,0.002930943],"genre_scores_gemma":[0.8163434,0.0002660607,0.1812816,0.00009671589,0.00002801701,0.0001996142,0.0002391768,0.0001020574,0.001443351],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01517625,"threshold_uncertainty_score":0.03017581,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04756454524991755,"score_gpt":0.3385360643285482,"score_spread":0.2909715190786307,"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."}}