{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001009859,0.0009055311,0.000979194,0.0005481923,0.0003672242,0.000939156,0.001289345,0.001103279,0.002328387],"category_scores_gemma":[0.006557437,0.0007087516,0.0006140697,0.0006632474,0.001556429,0.002216581,0.001765512,0.002158036,0.0002957312],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001130246,"about_ca_system_score_gemma":0.001528716,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006310435,"about_ca_topic_score_gemma":0.00644423,"domain_scores_codex":[0.999328,0.0002376546,0.00003549402,0.0001462746,0.0001854379,0.00006708978],"domain_scores_gemma":[0.9972165,0.00200525,0.000245294,0.0002895117,0.0001712622,0.00007226419],"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":[0.00005951306,0.00002427054,0.0002023287,0.00005187228,0.00001523599,0.0000500284,0.0000679678,0.9387379,0.0007611546,0.0357455,0.000799688,0.02348458],"study_design_scores_gemma":[0.000005394124,0.000008023008,0.00002112245,0.000004637984,0.000001759974,0.00000570719,0.00000460978,0.9824219,0.0002547217,0.01707414,0.0001952237,0.000002698321],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01009594,0.0001439674,0.9872875,0.0002748982,0.00002111105,0.0000375825,0.0001042358,0.0004737969,0.001560865],"genre_scores_gemma":[0.7004469,0.0003733189,0.295392,0.0002100804,0.00007442755,0.0002958602,0.0005593043,0.0001707891,0.002477403],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006310435,"threshold_uncertainty_score":0.01254743,"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."}}