{"id":"W3092954297","doi":"10.48550/arxiv.2010.09163","title":"D2RL: Deep Dense Architectures in Reinforcement Learning","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Reinforcement learning; Suite; Computer science; Artificial intelligence; Benchmark (surveying); Deep learning; Architecture; Variety (cybernetics); Artificial neural network; Reinforcement; Unsupervised learning; Generative grammar; Machine learning; Human–computer interaction; Engineering","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003050217,0.0004557743,0.0004589601,0.0004855132,0.0001585642,0.0002116867,0.002508952,0.000303402,0.00004889126],"category_scores_gemma":[0.0001970548,0.0005502815,0.0001939405,0.0008178547,0.0001001111,0.0001866258,0.00409224,0.001971247,0.0001920329],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003732867,"about_ca_system_score_gemma":0.0002153986,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001464565,"about_ca_topic_score_gemma":0.00004091161,"domain_scores_codex":[0.9972414,0.0002693043,0.0003935561,0.001269965,0.0002265589,0.0005992307],"domain_scores_gemma":[0.9979746,0.0001787002,0.0004008892,0.001110867,0.00009182598,0.000243072],"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":[0.00002830944,0.00001457612,0.003231454,0.00008766793,0.00005664203,0.0006080861,0.001026317,0.9683433,0.00003064052,0.02615407,0.00004480738,0.0003741367],"study_design_scores_gemma":[0.0005137653,0.0001335059,0.001157145,0.0001190797,0.00002911156,0.00000486816,0.00007475728,0.9917208,0.00008499139,0.004850613,0.000765635,0.0005457326],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04155404,0.00003908504,0.9515387,0.000232196,0.000358433,0.0003860661,4.148363e-7,0.0004278347,0.005463236],"genre_scores_gemma":[0.9940503,0.00009680992,0.003686407,0.000255183,0.00007199157,0.000001732769,0.00001772198,0.00003168964,0.001788164],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9524962,"threshold_uncertainty_score":0.9996949,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06018814793559971,"score_gpt":0.1946036012157587,"score_spread":0.134415453280159,"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."}}