{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009845094,0.0001374282,0.0001308524,0.00007042507,0.0001845201,0.0001060612,0.0005803494,0.0000549786,0.00004012889],"category_scores_gemma":[0.00008245998,0.0001577116,0.00004578442,0.0005082201,0.00006092105,0.0006302348,0.0005637366,0.0002371353,0.0001633139],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000432812,"about_ca_system_score_gemma":0.0000305935,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001092437,"about_ca_topic_score_gemma":9.63969e-7,"domain_scores_codex":[0.9990692,0.00004976272,0.0001310452,0.0004024931,0.00008638432,0.000261177],"domain_scores_gemma":[0.9992947,0.00006377595,0.0001033653,0.0002679393,0.00005192941,0.0002183133],"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":[0.000007515727,0.000002641607,0.004511823,0.00001189517,0.00001631314,0.00005557373,0.0005419826,0.8920544,0.00003887982,0.1022843,0.00005552396,0.0004191428],"study_design_scores_gemma":[0.0004238095,0.000179443,0.0006293469,0.000007375989,0.00001137221,0.000003001405,0.0001332005,0.993696,0.00006621551,0.0001891655,0.004477275,0.0001838283],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01786958,0.00001698271,0.9735904,0.0003014156,0.00006024542,0.00009568706,3.996191e-8,0.000247451,0.007818173],"genre_scores_gemma":[0.9960166,0.00006297465,0.001901234,0.000596428,0.00002867989,1.672881e-7,0.000001705585,0.000007861526,0.001384339],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.978147,"threshold_uncertainty_score":0.6431293,"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."}}