{"id":"W4296474750","doi":"10.1109/cog51982.2022.9893546","title":"Mitigating Cowardice for Reinforcement Learning Agents in Combat Scenarios","year":2022,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Cowardice; Reinforcement learning; Computer science; Reinforcement; Computer security; Artificial intelligence; Engineering; Geography","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":[0.0009414246,0.0001481058,0.0001840076,0.0001813447,0.0005592041,0.0001415207,0.0009479527,0.00002904956,0.0001916605],"category_scores_gemma":[0.0001718585,0.0001638089,0.0000808798,0.0004711534,0.00002110557,0.0003100283,0.001034587,0.0004102022,0.00002458661],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002721227,"about_ca_system_score_gemma":0.00008415439,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000724142,"about_ca_topic_score_gemma":0.000003134124,"domain_scores_codex":[0.998033,0.0001284951,0.0004275822,0.0003637582,0.0005673162,0.0004797839],"domain_scores_gemma":[0.9991028,0.0002287808,0.000182211,0.0003607293,0.00005012881,0.00007532366],"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":[0.000005786607,0.00001487198,0.003258471,0.00001865149,0.00001131576,0.000006936928,0.001027943,0.9791692,0.00008964579,0.01372749,0.001109757,0.001559951],"study_design_scores_gemma":[0.000872497,0.0002869652,0.0005210842,0.00001484803,0.00000331276,0.000006166139,0.0004176935,0.97356,0.0001512622,0.0001192661,0.02384589,0.0002009753],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005910056,0.00001627692,0.982662,0.0005964076,0.0004000473,0.0005776958,3.019463e-7,0.0002093204,0.009627848],"genre_scores_gemma":[0.95851,0.000003433327,0.03182885,0.0011469,0.00002551482,0.0001928438,0.00002064831,0.00001723329,0.008254519],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9526,"threshold_uncertainty_score":0.6679934,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03762955635733645,"score_gpt":0.2827725526344957,"score_spread":0.2451429962771593,"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."}}