{"id":"W2561828331","doi":"10.1609/aaai.v30i1.10304","title":"Compressed Conditional Mean Embeddings for Model-Based Reinforcement Learning","year":2016,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Reinforcement learning; Markov decision process; Class (philosophy); Context (archaeology); Kernel (algebra); Bottleneck; Mathematical optimization; Artificial intelligence; Machine learning; Markov process; Mathematics","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":[0.00104686,0.0008985607,0.001159769,0.0004722524,0.0003160025,0.0007205551,0.001437333,0.001111227,0.003329316],"category_scores_gemma":[0.006229788,0.0005480421,0.0006712794,0.000472966,0.001106267,0.001763941,0.001754991,0.002693399,0.0004564701],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001041954,"about_ca_system_score_gemma":0.001279106,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003391833,"about_ca_topic_score_gemma":0.002827147,"domain_scores_codex":[0.9994661,0.0002048931,0.00002444471,0.0001047475,0.0001443793,0.0000554472],"domain_scores_gemma":[0.9976484,0.001607551,0.0002167615,0.0002444298,0.0001808685,0.0001019139],"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":[0.0000489071,0.00004074966,0.0002082527,0.00004367633,0.00001926461,0.00002890559,0.00003201474,0.9488815,0.0006134252,0.0281145,0.0007699412,0.02119881],"study_design_scores_gemma":[0.000003162567,0.00000851326,0.00001054811,0.000002032755,0.000001303836,0.00000364653,0.000001116337,0.9916416,0.000143932,0.008048518,0.000133538,0.000002033661],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006362659,0.00009670664,0.9920339,0.0001549337,0.00002380104,0.00001786961,0.00004352854,0.0004139829,0.0008525567],"genre_scores_gemma":[0.7011598,0.0002217882,0.2948527,0.0002210396,0.00007506736,0.0002462193,0.0003190705,0.0002381069,0.002666261],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003391833,"threshold_uncertainty_score":0.01113766,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07598492911930667,"score_gpt":0.3017610321490101,"score_spread":0.2257761030297035,"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."}}