{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001274964,0.001398735,0.0008559019,0.0004126461,0.0003208203,0.0007535883,0.00114485,0.0008702945,0.001612975],"category_scores_gemma":[0.003915837,0.0004443908,0.0003666076,0.0002268274,0.0008548691,0.000707841,0.000834687,0.001632402,0.0003666428],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008643726,"about_ca_system_score_gemma":0.001090461,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006565301,"about_ca_topic_score_gemma":0.007202276,"domain_scores_codex":[0.9995816,0.0001110101,0.00002334275,0.00009960728,0.0001181731,0.00006623131],"domain_scores_gemma":[0.9988845,0.0006247705,0.0001317051,0.00008084784,0.0002023805,0.00007571434],"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":[0.00008102531,0.00003930711,0.0004165705,0.0000390655,0.00003053796,0.00006067671,0.00002991839,0.9679232,0.002104189,0.002062658,0.0005877245,0.02662513],"study_design_scores_gemma":[0.000003149147,0.00001040281,0.00002792826,0.000002420956,0.00000307713,0.000004259756,0.000001563847,0.9991059,0.000324028,0.0004313964,0.00008442505,0.000001546002],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0440102,0.0005886922,0.9485874,0.0003130229,0.0001385401,0.00007577857,0.00004268716,0.001516204,0.004727587],"genre_scores_gemma":[0.9494313,0.00014411,0.04649359,0.0002094095,0.0000460685,0.00008875618,0.00007012694,0.00008523105,0.003431424],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006565301,"threshold_uncertainty_score":0.01305419,"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."}}