{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002012068,0.0008951784,0.001462111,0.0005444717,0.0005013823,0.0008631673,0.001220355,0.001228384,0.001653667],"category_scores_gemma":[0.009687849,0.0006176473,0.000598077,0.0008107098,0.001541239,0.001324117,0.00111844,0.001817472,0.0001947799],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001386136,"about_ca_system_score_gemma":0.001385054,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01371115,"about_ca_topic_score_gemma":0.00753094,"domain_scores_codex":[0.9991847,0.0003828589,0.00003435228,0.0001086339,0.0002124008,0.00007714519],"domain_scores_gemma":[0.9957581,0.003372788,0.0002768066,0.0001102927,0.000321214,0.000160758],"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":[0.00003825296,0.00003255964,0.0003392447,0.00004900917,0.0000210788,0.0000464198,0.00004547033,0.9686453,0.00023513,0.01647742,0.0002701776,0.01379982],"study_design_scores_gemma":[0.0000118079,0.00001017218,0.00004211904,0.000003865478,0.000003096376,0.00000420301,0.000002967456,0.9901438,0.00006667147,0.009556461,0.0001513909,0.000003435085],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01375947,0.0006105661,0.9834155,0.0003427877,0.00004358443,0.00002600979,0.00002870438,0.0002234501,0.001549901],"genre_scores_gemma":[0.7865179,0.0008696203,0.2095966,0.0001493982,0.000107481,0.0002115863,0.0001017435,0.00007818347,0.002367523],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01371115,"threshold_uncertainty_score":0.02726269,"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."}}