{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001254197,0.0001233215,0.000153186,0.00002688758,0.00009266581,0.00007274236,0.0005520114,0.0003647256,0.00002667627],"category_scores_gemma":[0.0001020871,0.0001238732,0.00006203735,0.0005112364,0.00002586024,0.0003473492,0.0001903805,0.001480309,0.00001552104],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005458733,"about_ca_system_score_gemma":0.0001100498,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006870286,"about_ca_topic_score_gemma":1.158803e-7,"domain_scores_codex":[0.9988515,0.00004181936,0.0002708015,0.000238469,0.0003973989,0.0001999713],"domain_scores_gemma":[0.9993131,0.00003530781,0.0002346632,0.0002284794,0.0001085471,0.00007993104],"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":[0.000003112049,0.000003845925,0.0005735282,0.00003470875,0.00001569003,0.00000398425,0.0006551655,0.9834239,0.004911462,0.009381237,0.00007731764,0.0009160832],"study_design_scores_gemma":[0.0001952881,0.0001455988,0.0003433974,0.00003555523,0.00000919907,0.000004364529,0.00005334196,0.9915751,0.004171271,0.0000325549,0.003305055,0.0001292555],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02558101,0.0001341505,0.9707657,0.0004715101,0.000194659,0.0001373047,2.227059e-7,0.0001662504,0.002549255],"genre_scores_gemma":[0.9481514,0.000003795101,0.05093965,0.0007097254,0.00005836394,0.000001240036,0.000006656787,0.000009954401,0.0001192131],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9225704,"threshold_uncertainty_score":0.6431289,"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."}}