{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000339609,0.000229881,0.0002757295,0.0001091144,0.0002611412,0.0004875441,0.000372408,0.00007827125,0.00006232362],"category_scores_gemma":[0.0001761523,0.0002084299,0.0000625339,0.000263949,0.00004116635,0.0004129029,0.0003553705,0.0003657741,0.00008409088],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006288122,"about_ca_system_score_gemma":0.00007157344,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001421234,"about_ca_topic_score_gemma":0.000002909743,"domain_scores_codex":[0.9980921,0.0001409155,0.0003170009,0.0005436449,0.0004564851,0.0004499003],"domain_scores_gemma":[0.998917,0.0001587073,0.00009124178,0.0005311082,0.0001416282,0.0001602745],"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":[0.000009821094,0.00001321466,0.005948067,0.00001319095,0.00004976062,0.00005147952,0.0006445996,0.9578801,0.0001919612,0.02797408,0.0001599613,0.007063776],"study_design_scores_gemma":[0.001098348,0.0002527752,0.001164951,0.00005886958,0.00001205882,0.00006347201,0.00006560103,0.9910529,0.0002810785,0.00004022088,0.005646084,0.0002636761],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001966821,0.00009516179,0.9800656,0.0007402187,0.0002475936,0.0001603718,3.165884e-8,0.000280781,0.01644335],"genre_scores_gemma":[0.8199884,0.00003772236,0.1716771,0.002501303,0.00008029413,0.00001272828,0.000003833203,0.00001943692,0.005679153],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8180216,"threshold_uncertainty_score":0.8499524,"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."}}