{"id":"W3104132897","doi":"","title":"Deep Reinforcement and InfoMax Learning","year":2020,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Infomax; Reinforcement learning; Computer science; Artificial intelligence; Task (project management); Representation (politics); Machine learning; Mutual information; Baseline (sea); Channel (broadcasting)","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":[0.001644287,0.001095103,0.0007948678,0.0004173072,0.0002868951,0.0007942126,0.001760586,0.001354387,0.002438398],"category_scores_gemma":[0.005142001,0.0003502646,0.0003940898,0.0003891944,0.001481261,0.001667802,0.001413825,0.002240217,0.0004395495],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001212325,"about_ca_system_score_gemma":0.001158652,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002723642,"about_ca_topic_score_gemma":0.00329351,"domain_scores_codex":[0.9995224,0.0001712175,0.00002233629,0.0001147222,0.00009902903,0.00007029003],"domain_scores_gemma":[0.9983044,0.0009961065,0.000190112,0.0002097459,0.0001625233,0.0001371706],"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":[0.0002628859,0.0001191352,0.001176549,0.00009376946,0.00006233337,0.00007032834,0.00004306595,0.9077311,0.002669583,0.03080609,0.002358555,0.05460654],"study_design_scores_gemma":[0.00001083277,0.00003038744,0.00008388905,0.000005406404,0.000003921908,0.000006632535,0.00000215738,0.9893621,0.000906634,0.009297369,0.0002865777,0.000004190786],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08111986,0.0006782233,0.906459,0.001491341,0.0001273871,0.00006433182,0.00032391,0.001960453,0.007775378],"genre_scores_gemma":[0.8986264,0.0001763154,0.09691522,0.0003330225,0.00006448563,0.0001032194,0.0002632742,0.00009821348,0.003419806],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002723642,"threshold_uncertainty_score":0.008796096,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05192380332967931,"score_gpt":0.1673757088892988,"score_spread":0.1154519055596195,"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."}}