{"id":"W2111680853","doi":"","title":"A planning algorithm for predictive state representations","year":2003,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Partially observable Markov decision process; Observable; Representation (politics); Markov decision process; Computer science; State (computer science); Sequence (biology); Mathematical optimization; Markov process; Process (computing); Algorithm; Mathematics; Statistics","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":[0.001211469,0.001004557,0.000941233,0.0007300221,0.0007036264,0.001177961,0.001925487,0.001596546,0.005580661],"category_scores_gemma":[0.004206386,0.0006309439,0.000978425,0.0008967304,0.00119525,0.00225942,0.001965987,0.002313576,0.001094476],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001006133,"about_ca_system_score_gemma":0.001939456,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003704174,"about_ca_topic_score_gemma":0.003265294,"domain_scores_codex":[0.999252,0.0002067311,0.00003878862,0.0002098697,0.0002115717,0.00008094951],"domain_scores_gemma":[0.9990877,0.0006115537,0.0000540178,0.0001075668,0.00009758356,0.00004152304],"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":[0.00006385968,0.00008509084,0.0002805657,0.0001090212,0.0000370408,0.0001137764,0.0001564142,0.6483837,0.001371587,0.1797816,0.004179731,0.1654376],"study_design_scores_gemma":[0.00001687658,0.00001744514,0.0000184865,0.00001177759,0.000007790128,0.00001898024,0.000009715675,0.955848,0.0005283564,0.04093526,0.002581403,0.000005920473],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001394454,0.00007211813,0.9960023,0.00009925108,0.00002198291,0.00004167239,0.00002718092,0.0004144553,0.001926649],"genre_scores_gemma":[0.1240016,0.0002508101,0.8714055,0.0001187391,0.0000475097,0.0004167088,0.0001886867,0.0001728042,0.003397642],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005580661,"threshold_uncertainty_score":0.01866919,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02729771844446384,"score_gpt":0.3026270110575934,"score_spread":0.2753292926131296,"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."}}