{"id":"W2928034659","doi":"10.1109/icpr48806.2021.9412212","title":"Deep Reinforcement Learning on a Budget: 3D Control and Reasoning Without a Supercomputer","year":2021,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; College of Natural Resources and Sciences, Humboldt State University; Agence Nationale de la Recherche","keywords":"Computer science; Reinforcement learning; Artificial intelligence; Robotics; High fidelity; Deep learning; Suite; Human–computer interaction; Fidelity; Distributed computing; Machine learning; Robot","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007547914,0.0005921334,0.0005705364,0.000218121,0.0003826549,0.0007719686,0.001474243,0.0008497653,0.007778412],"category_scores_gemma":[0.002405695,0.0004716442,0.0004954292,0.0002983988,0.000975573,0.001447214,0.001593856,0.001643503,0.001015798],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001139145,"about_ca_system_score_gemma":0.0009542012,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0124849,"about_ca_topic_score_gemma":0.01315462,"domain_scores_codex":[0.9997222,0.00007716454,0.00001377124,0.00006479774,0.00007980473,0.00004218223],"domain_scores_gemma":[0.9994735,0.0002265562,0.00003370163,0.0001314407,0.00007165729,0.00006313646],"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":[0.0001447818,0.00004867008,0.0003604167,0.0000347712,0.00001811999,0.00005878239,0.00003366125,0.9534668,0.001914141,0.009209968,0.002891781,0.03181802],"study_design_scores_gemma":[0.00001015202,0.00001278841,0.00004098434,0.000002446529,0.000001581177,0.000003549628,0.000002813525,0.9959363,0.0004250814,0.003048499,0.00051405,0.000001746427],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05593888,0.0002404587,0.9287863,0.0007567216,0.0001300491,0.00008302424,0.0002944813,0.003826011,0.009944067],"genre_scores_gemma":[0.7602599,0.0001902313,0.2326516,0.0002490534,0.00003344545,0.000212755,0.0006492148,0.0003321619,0.005421652],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0124849,"threshold_uncertainty_score":0.02602136,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008855926514395013,"score_gpt":0.2307316679909199,"score_spread":0.2218757414765249,"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."}}