{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001503603,0.0009575918,0.0007879137,0.0003734519,0.0003325082,0.001005163,0.001888657,0.001363464,0.006266187],"category_scores_gemma":[0.004857422,0.0005919402,0.0004812796,0.0004238769,0.001114377,0.001496889,0.002090071,0.002783957,0.001367038],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001240421,"about_ca_system_score_gemma":0.001322629,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004682967,"about_ca_topic_score_gemma":0.006036348,"domain_scores_codex":[0.9994999,0.0001780951,0.0000250358,0.0001124505,0.0001308893,0.00005360089],"domain_scores_gemma":[0.9988471,0.0006796325,0.00008899505,0.0001660927,0.0001275025,0.00009066339],"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":[0.000138298,0.0001068689,0.0008235936,0.0001939248,0.00006436774,0.0000844787,0.00006609621,0.835149,0.002438237,0.0487108,0.008565383,0.103659],"study_design_scores_gemma":[0.00002652527,0.00002556,0.00004736585,0.00001248654,0.000004547436,0.0000108717,0.000003429613,0.9730492,0.0006951495,0.02449798,0.001622049,0.000004958209],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009602013,0.0006971835,0.9810338,0.0006145967,0.000101919,0.0000579952,0.0002287991,0.00311307,0.004550686],"genre_scores_gemma":[0.5825522,0.0007715725,0.4050829,0.0006714911,0.000105973,0.0006115416,0.000836968,0.0008474163,0.008520094],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006266187,"threshold_uncertainty_score":0.02096248,"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."}}