{"id":"W4297822508","doi":"10.48550/arxiv.2103.02142","title":"Learning to Fly -- a Gym Environment with PyBullet Physics for\\n Reinforcement Learning of Multi-agent Quadcopter Control","year":2021,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; Institute for Christian Studies; University of Toronto","funders":"","keywords":"Reinforcement learning; Computer science; Software portability; Artificial intelligence; Human–computer interaction; Physics engine; Machine learning; Operating system","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":[0.0006459296,0.0006809845,0.0005964331,0.0003476173,0.0005885597,0.000865061,0.002004101,0.0009344696,0.03302044],"category_scores_gemma":[0.001769273,0.0005511469,0.001065588,0.000263785,0.0009858002,0.001951667,0.002717335,0.002408804,0.006478161],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005642841,"about_ca_system_score_gemma":0.001395238,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002203838,"about_ca_topic_score_gemma":0.003592595,"domain_scores_codex":[0.9997501,0.00004255064,0.00001675084,0.00006349683,0.00009458917,0.00003246554],"domain_scores_gemma":[0.9996219,0.0001483938,0.00002342172,0.00008450315,0.00002908,0.00009266544],"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":[0.00108186,0.0009276001,0.004164353,0.000705868,0.0001478656,0.0009535249,0.000756547,0.3986495,0.03557915,0.1304753,0.07830443,0.348254],"study_design_scores_gemma":[0.0002771594,0.0001712874,0.00151247,0.00006898765,0.00001822567,0.0001917746,0.00004824223,0.7819519,0.01255918,0.06205875,0.1410715,0.00007045903],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01562067,0.0001832272,0.8913734,0.0007299128,0.0001673564,0.0002468551,0.001496552,0.07268029,0.01750179],"genre_scores_gemma":[0.2664222,0.000335413,0.7029899,0.0005016895,0.00006805811,0.0009692926,0.002513829,0.008464671,0.01773502],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03302044,"threshold_uncertainty_score":0.1104644,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05253152417695468,"score_gpt":0.1886284227640568,"score_spread":0.1360968985871021,"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."}}