{"id":"W4288047783","doi":"10.1109/icuas54217.2022.9836052","title":"Soft Actor-Critic with Inhibitory Networks for Retraining UAV Controllers Faster","year":2022,"lang":"en","type":"article","venue":"2022 International Conference on Unmanned Aircraft Systems (ICUAS)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Lockheed Martin (Canada)","funders":"","keywords":"Computer science; Retraining; Distributed computing; Control engineering; Engineering; Business","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":[],"category_scores_codex":[0.0009661343,0.000401471,0.0004626741,0.0004030081,0.0006142262,0.0006391537,0.002005503,0.0001074015,0.0003367191],"category_scores_gemma":[0.0001323538,0.0003858533,0.0001495475,0.0003421378,0.00009325768,0.0005754103,0.0004930355,0.0007530651,0.00003916369],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005217356,"about_ca_system_score_gemma":0.0002874687,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002327656,"about_ca_topic_score_gemma":0.000006886649,"domain_scores_codex":[0.9960177,0.000293112,0.0007097179,0.0008600665,0.001468767,0.0006506438],"domain_scores_gemma":[0.9977055,0.000469582,0.0004741945,0.0006668912,0.0005100227,0.0001738422],"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":[0.0002561839,0.00007182443,0.000410953,0.0000418433,0.0002451813,0.00004889899,0.0007262789,0.8630658,0.0004026806,0.1265147,0.00746424,0.0007514481],"study_design_scores_gemma":[0.002002963,0.001100008,0.00009804992,0.0001781884,0.00001912511,0.00005504614,0.001277586,0.9765835,0.00002658758,0.0001579656,0.01802436,0.0004766573],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001610549,0.00008033049,0.9755118,0.002822856,0.005953085,0.001180831,0.00005012406,0.0003459783,0.01244444],"genre_scores_gemma":[0.9868697,0.000007990459,0.0009536343,0.0009751965,0.0004828911,0.0007246283,0.0001267739,0.00005175179,0.009807437],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9852592,"threshold_uncertainty_score":0.9998593,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03033807866002263,"score_gpt":0.2564925657908325,"score_spread":0.2261544871308098,"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."}}