{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006596077,0.0007568788,0.001187355,0.0005259905,0.0004029059,0.0009260715,0.00174553,0.001048721,0.005281249],"category_scores_gemma":[0.002124468,0.0008698567,0.0008051521,0.001093288,0.0009535367,0.001566892,0.001251586,0.001753963,0.0008728281],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008395631,"about_ca_system_score_gemma":0.0007012503,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006082502,"about_ca_topic_score_gemma":0.006154992,"domain_scores_codex":[0.9996862,0.00007277595,0.00002312809,0.00006708343,0.0001183304,0.00003248076],"domain_scores_gemma":[0.999438,0.0003896409,0.00002702638,0.00006793872,0.00005924297,0.00001815472],"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":[0.00006179087,0.00002347082,0.00009396184,0.0001097106,0.0000244837,0.0000522758,0.00006720454,0.8385354,0.001307863,0.0641863,0.001513433,0.09402411],"study_design_scores_gemma":[0.000004730368,0.00001125281,0.00002075374,0.000008387549,0.000004105859,0.000008959018,0.000004332476,0.9639859,0.000383663,0.03496114,0.000602224,0.000004610181],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003267278,0.0003257722,0.9935814,0.00004055578,0.00002559224,0.00002087862,0.00004268248,0.0003549167,0.002340869],"genre_scores_gemma":[0.4335136,0.001386796,0.5544614,0.00008562543,0.00005920114,0.000368449,0.0004475819,0.0002620739,0.009415178],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006082502,"threshold_uncertainty_score":0.01766753,"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."}}