{"id":"W3107153805","doi":"10.1038/s41586-020-2939-8","title":"Autonomous navigation of stratospheric balloons using reinforcement learning","year":2020,"lang":"en","type":"article","venue":"Nature","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":272,"is_retracted":false,"has_abstract":false,"ca_institutions":"Google (Canada)","funders":"","keywords":"Reinforcement learning; Computer science; Controller (irrigation); Obstacle avoidance; Process (computing); Obstacle; Reinforcement; Real-time computing; Artificial intelligence; Simulation; 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":[0.0004528383,0.0003290128,0.0004206077,0.0002129007,0.0002864903,0.0004278577,0.0005455865,0.0005574573,0.0007548871],"category_scores_gemma":[0.001864032,0.000207469,0.0002405316,0.0001554057,0.0007902462,0.0004683564,0.0006220657,0.0006957601,0.0001243544],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004604977,"about_ca_system_score_gemma":0.0006066091,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005956338,"about_ca_topic_score_gemma":0.004279956,"domain_scores_codex":[0.9998683,0.00004910498,0.000005249321,0.00002498924,0.0000298148,0.00002260175],"domain_scores_gemma":[0.9994272,0.0003073553,0.00008560234,0.00004329403,0.00008747062,0.00004914032],"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":[0.00006672545,0.00003282067,0.001003031,0.00001913475,0.00002227694,0.00003159546,0.00003363698,0.9693455,0.002501015,0.004500513,0.0003795556,0.02206422],"study_design_scores_gemma":[0.000007026286,0.0000204762,0.00009229728,0.000001713279,0.00000245206,0.000004731431,0.000003212937,0.9975436,0.0002801113,0.001898454,0.0001437468,0.000002136719],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1809496,0.0004026699,0.8118282,0.0004650708,0.0001176719,0.00004497914,0.00003114144,0.000548619,0.005611976],"genre_scores_gemma":[0.9769408,0.00006760935,0.02189173,0.0000370136,0.00001327749,0.0000229893,0.00001683959,0.00001454768,0.0009952608],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005956338,"threshold_uncertainty_score":0.01184338,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01814971253088397,"score_gpt":0.2613037861494292,"score_spread":0.2431540736185452,"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."}}