{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.001094421,0.001305415,0.001630046,0.0004273145,0.0008208071,0.0004280406,0.002465639,0.0005053565,0.0002499177],"category_scores_gemma":[0.0002223342,0.001516218,0.00083834,0.0008830095,0.0003789869,0.0006267671,0.003146121,0.002055082,0.0001832978],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00118929,"about_ca_system_score_gemma":0.0006685418,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001971681,"about_ca_topic_score_gemma":0.000009518834,"domain_scores_codex":[0.9929332,0.0006826773,0.001230454,0.002912863,0.0007208926,0.001519943],"domain_scores_gemma":[0.9937513,0.0005940889,0.002041487,0.002189568,0.0007270857,0.0006965106],"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":[0.0005316378,0.0002700313,0.007318414,0.0004925147,0.001105284,0.0001876187,0.005734474,0.9788123,0.0003393994,0.003757178,0.00002165566,0.0014295],"study_design_scores_gemma":[0.005500058,0.003023725,0.0006424722,0.0008917978,0.0006575925,0.000007002764,0.002224849,0.9808536,0.0007524622,0.00002443494,0.003877864,0.001544107],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04955108,0.00005904479,0.9465839,0.000117652,0.000494596,0.002559046,0.000005904732,0.000157142,0.0004716264],"genre_scores_gemma":[0.9626438,0.0003349516,0.02369009,0.0002193007,0.0001353009,0.00002623268,0.00007564414,0.0001235008,0.01275116],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9228938,"threshold_uncertainty_score":0.9999697,"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."}}