{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001878313,0.00006994529,0.00006969636,0.00006154244,0.0001273576,0.000113714,0.0002579806,0.00001976384,0.00001824274],"category_scores_gemma":[0.000119708,0.00006500852,0.00003562855,0.000179653,0.00001794192,0.0003400438,0.00004809861,0.0000613558,0.0000191888],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002425571,"about_ca_system_score_gemma":0.0000511625,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004313828,"about_ca_topic_score_gemma":1.737663e-7,"domain_scores_codex":[0.9992413,0.00003260815,0.0001477665,0.0002163522,0.0001559012,0.0002061002],"domain_scores_gemma":[0.9993379,0.0001824956,0.00005727893,0.0002832483,0.00008477518,0.00005427306],"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":[0.000001024986,0.00001049398,0.0004404988,0.000002941039,0.0000245023,0.000002974801,0.001049489,0.9494885,0.00001618094,0.03832512,0.002630677,0.008007609],"study_design_scores_gemma":[0.0002693316,0.00009420678,0.0002412762,0.000005197305,0.000003074188,0.000004615709,0.00009374023,0.9880543,0.0008790237,0.003562512,0.006708436,0.00008426569],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00004224664,0.00001156432,0.9689895,0.00007835319,0.0002267213,0.0002495921,0.000001438062,0.0001808634,0.03021972],"genre_scores_gemma":[0.02046908,0.000002057111,0.9685926,0.0001879852,0.00001837032,0.00005547962,0.000003868108,0.000007802761,0.01066279],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.03856583,"threshold_uncertainty_score":0.2650971,"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."}}