{"id":"W2574782009","doi":"","title":"Learning multi-step predictive state representations","year":2016,"lang":"en","type":"article","venue":"International Joint Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Exploit; Observable; Dynamical systems theory; Variety (cybernetics); Representation (politics); Artificial intelligence; Class (philosophy); Machine learning; State (computer science); Theoretical computer science; Algorithm","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003885766,0.0002344163,0.0001849056,0.0003049737,0.0001883491,0.0003983823,0.001265121,0.00006849565,0.0006014592],"category_scores_gemma":[0.001062562,0.0001839404,0.0001094399,0.0002547211,0.0001862498,0.000796593,0.0003659448,0.0003201067,0.002005688],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001839269,"about_ca_system_score_gemma":0.0001358317,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005760345,"about_ca_topic_score_gemma":0.00002494591,"domain_scores_codex":[0.9973602,0.0001510092,0.0006664427,0.0006692056,0.0007747164,0.0003784501],"domain_scores_gemma":[0.9980032,0.0003342296,0.0003281471,0.0005048373,0.000681102,0.0001485033],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004867071,0.0001200722,0.0005680625,0.000003276986,0.00007040185,0.00003267021,0.001157341,0.1703261,0.00882121,0.5415319,0.0001550462,0.2771652],"study_design_scores_gemma":[0.00009579534,0.0003160192,0.001119562,0.0001571621,0.000004404999,0.000009683787,0.0002724613,0.9432174,0.03455244,0.0189162,0.001036088,0.0003028083],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001477673,0.000002648047,0.9795387,0.005755121,0.001314999,0.0002265037,0.000008641277,0.0003227819,0.01135289],"genre_scores_gemma":[0.9710233,0.00007264403,0.02271799,0.0002136041,0.000107029,0.00004423832,0.000006420093,0.00001659323,0.00579814],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9695457,"threshold_uncertainty_score":0.9987714,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.121939934642129,"score_gpt":0.3447195660178371,"score_spread":0.2227796313757081,"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."}}