{"id":"W3125267060","doi":"10.2514/1.a34838","title":"Deep Reinforcement Learning for Spacecraft Proximity Operations Guidance","year":2021,"lang":"en","type":"article","venue":"Journal of Spacecraft and Rockets","topic":"Space Satellite Systems and Control","field":"Engineering","cited_by":103,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Spacecraft; Computer science; Artificial intelligence; Controller (irrigation); Simulation; Flight simulator; Control engineering; Aerospace engineering; Engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002623707,0.0001542768,0.0003149294,0.00007872158,0.0001634788,0.00009433932,0.0000702715,0.0000847723,0.00003512013],"category_scores_gemma":[0.00009592842,0.0001309165,0.0001302056,0.000106836,0.00001464195,0.0002751306,0.00002270401,0.000227848,0.000003569148],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005233719,"about_ca_system_score_gemma":0.00005899026,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004629887,"about_ca_topic_score_gemma":0.0000910537,"domain_scores_codex":[0.9990511,0.00002634894,0.0003882769,0.0001100444,0.0001864334,0.0002378083],"domain_scores_gemma":[0.9992931,0.00004933217,0.00009138155,0.0001095887,0.0003141904,0.0001424343],"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":[0.00008228655,0.00005308319,0.004513936,0.0004292559,0.0004704455,0.00009129066,0.002483113,0.8883525,0.08378283,0.0005871018,0.003055383,0.01609884],"study_design_scores_gemma":[0.003462445,0.0004102436,0.003300894,0.0004551451,0.0001780808,0.0005055001,0.002652803,0.7653484,0.01903658,0.00017751,0.2039213,0.0005511469],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1834936,0.03004449,0.7790093,0.003056367,0.00152218,0.0005576066,0.000001979201,0.00009869672,0.002215808],"genre_scores_gemma":[0.9922338,0.001225281,0.003185849,0.00005543117,0.000456095,0.00001416963,0.00000275453,0.00002781059,0.00279884],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8087401,"threshold_uncertainty_score":0.5338619,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008570806722344435,"score_gpt":0.222012698461574,"score_spread":0.2134418917392296,"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."}}