{"id":"W2111833414","doi":"10.1109/robot.2008.4543641","title":"Bayesian reinforcement learning in continuous POMDPs with application to robot navigation","year":2008,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":68,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval; McGill University","funders":"","keywords":"Computer science; Reinforcement learning; Markov decision process; Particle filter; Partially observable Markov decision process; Robot; Artificial intelligence; Trajectory; Optimal control; Posterior probability; Bayesian probability; Mathematical optimization; Observable; Machine learning; Markov process; Markov chain; Kalman filter; Markov model; Mathematics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002291136,0.0001469128,0.0001557237,0.0001677423,0.000153382,0.00007331377,0.0004596122,0.00005008324,0.00001148531],"category_scores_gemma":[0.00002338526,0.0001314051,0.00002272655,0.0006729921,0.00002072008,0.0004163043,0.0001345779,0.0002036529,0.0001460734],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001412524,"about_ca_system_score_gemma":0.00006977919,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001286468,"about_ca_topic_score_gemma":0.00001080043,"domain_scores_codex":[0.9985559,0.0000419989,0.0003129413,0.0003567895,0.0004155706,0.0003167741],"domain_scores_gemma":[0.9992138,0.00004273611,0.0001194076,0.0004267672,0.00009003174,0.0001072242],"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":[0.000007082816,0.00001412916,0.01065018,0.000005892269,0.000005275956,0.00001206618,0.001214416,0.9797261,0.0003277338,0.005538478,0.00005906884,0.002439606],"study_design_scores_gemma":[0.0004411508,0.0003644296,0.007221822,0.00003411823,0.000002230624,0.00003608959,0.00005718794,0.9878868,0.001096231,0.00002368121,0.002610317,0.0002259387],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007573664,0.000003733168,0.9808598,0.0005037441,0.00004101474,0.0004931939,1.773056e-8,0.000384247,0.0101406],"genre_scores_gemma":[0.8772706,0.000004108262,0.119972,0.0003093342,0.00002135074,0.00005836836,0.000008065602,0.00001125889,0.002344871],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.869697,"threshold_uncertainty_score":0.5358543,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009732780240815567,"score_gpt":0.2310888591736891,"score_spread":0.2213560789328735,"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."}}