{"id":"W1565405003","doi":"10.1007/978-3-540-68825-9_13","title":"Point-Based Planning for Predictive State Representations","year":2008,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"","keywords":"Observability; Computer science; Partially observable Markov decision process; Representation (politics); Observable; Markov decision process; Automated planning and scheduling; State (computer science); Point (geometry); Mathematical optimization; Artificial intelligence; Markov chain; Algorithm; Theoretical computer science; Markov process; Machine learning; Markov model; Mathematics; Applied 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006095468,0.000482889,0.0004554077,0.0009243846,0.0004853813,0.0004506361,0.002754473,0.0002123632,0.000009792891],"category_scores_gemma":[0.0002820154,0.0004788121,0.0001712638,0.0005136511,0.000665346,0.0006992167,0.0007010542,0.0007084435,0.00002046775],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003450894,"about_ca_system_score_gemma":0.0009248069,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009979569,"about_ca_topic_score_gemma":0.000004741132,"domain_scores_codex":[0.9961385,0.00003283872,0.0006076443,0.001451664,0.001042044,0.0007273242],"domain_scores_gemma":[0.9962648,0.001304185,0.0004544702,0.00138755,0.0004150579,0.0001739533],"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":[0.00001092931,0.000009462705,0.0000755549,0.00002532231,0.00001301484,0.00004789633,0.001080621,0.9713671,0.00001293404,0.001316522,0.0001676496,0.02587301],"study_design_scores_gemma":[0.0004322284,0.0003423315,0.0001042242,0.0003025326,0.000007763867,0.00002890067,2.25028e-7,0.9799962,0.0006579946,0.0159685,0.00167192,0.0004871789],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00001059026,0.0001376468,0.9936919,0.0005240921,0.001372619,0.0008653678,0.00001173817,0.0002750185,0.003111038],"genre_scores_gemma":[0.03585932,0.00002579981,0.9603595,0.001682932,0.0003612519,0.00005424738,0.00003287926,0.00006454792,0.001559486],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.03584873,"threshold_uncertainty_score":0.9997663,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02775704980736581,"score_gpt":0.2808852751791834,"score_spread":0.2531282253718176,"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."}}