{"id":"W2950653703","doi":"10.48550/arxiv.1312.0286","title":"Efficient Learning and Planning with Compressed Predictive States","year":2013,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Reinforcement learning; Artificial intelligence; Observable; A priori and a posteriori; Dimensionality reduction; Machine learning; Curse of dimensionality","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":[0.0001652212,0.0003376387,0.0003188361,0.0002308887,0.0002584084,0.0002939402,0.0008851367,0.0001727729,0.00001409361],"category_scores_gemma":[0.00003423569,0.0003340335,0.00005523673,0.0003000876,0.000181982,0.0001771519,0.002031912,0.0009557654,0.0000299233],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001205742,"about_ca_system_score_gemma":0.00009755264,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007376027,"about_ca_topic_score_gemma":6.734605e-7,"domain_scores_codex":[0.9981834,0.0001480972,0.0001700834,0.0009439354,0.0001562649,0.000398247],"domain_scores_gemma":[0.9984962,0.0002224529,0.0003355677,0.0005539539,0.0002135916,0.0001782522],"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":[0.00002579065,0.00001812359,0.01128225,0.00006585245,0.0001002317,0.000121515,0.001195574,0.9808943,0.000005906164,0.006189002,0.00004843623,0.00005301338],"study_design_scores_gemma":[0.0004755994,0.0001871336,0.002301102,0.0002557228,0.00004869902,0.000004567673,0.0004012255,0.9952729,0.00002291646,0.0004699913,0.0001791511,0.0003810446],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2828097,0.00004850505,0.7150533,0.00001882358,0.0001434486,0.000268423,0.000001487298,0.0002784561,0.001377878],"genre_scores_gemma":[0.9945115,0.00004820397,0.004030781,0.0000272439,0.00003207572,0.000001635811,0.0000156105,0.00002199991,0.001310912],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7117018,"threshold_uncertainty_score":0.9999112,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03664535695537425,"score_gpt":0.1825515416616542,"score_spread":0.14590618470628,"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."}}