{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006103294,0.000276173,0.0002931388,0.000159509,0.0003531101,0.0002303493,0.002065302,0.0001007492,0.0000720165],"category_scores_gemma":[0.0006530487,0.0001823457,0.0001902589,0.0003160739,0.000315644,0.000517995,0.0003098639,0.0002330086,0.00005734609],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001040702,"about_ca_system_score_gemma":0.0001732937,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004570547,"about_ca_topic_score_gemma":8.138613e-7,"domain_scores_codex":[0.9975587,0.00001665001,0.0006833859,0.000527366,0.0007376869,0.0004762631],"domain_scores_gemma":[0.9975371,0.0003260096,0.0006463347,0.0003198538,0.001058934,0.0001117547],"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":[0.00005435666,0.00002768202,0.00004065334,0.00003035506,0.00001245331,6.996357e-8,0.0002689673,0.3903491,0.03265378,0.5725426,0.0001539214,0.003866043],"study_design_scores_gemma":[0.00008381339,0.0002312618,0.000008996112,0.0002023669,0.000009429312,5.947544e-7,0.00005137629,0.6683707,0.2810228,0.04967131,0.0001678757,0.0001794229],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003757413,0.000002672624,0.9878541,0.003223718,0.0002140385,0.000588657,0.000003768397,0.0001453463,0.004210256],"genre_scores_gemma":[0.9826604,0.000006642977,0.01542868,0.0003287807,0.00005082115,0.00008571331,0.00000220424,0.0000196928,0.001417127],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9789029,"threshold_uncertainty_score":0.7435843,"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."}}