{"id":"W4293863350","doi":"10.1109/siu55565.2022.9864802","title":"Context Detection and Identification In Multi-Agent Reinforcement Learning With Non-Stationary Environment","year":2022,"lang":"en","type":"article","venue":"2022 30th Signal Processing and Communications Applications Conference (SIU)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Stantec (Canada)","funders":"","keywords":"Reinforcement learning; Identification (biology); Context (archaeology); Computer science; Artificial intelligence; Machine learning; 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":["sts"],"consensus_categories":[],"category_scores_codex":[0.0005826185,0.0001855066,0.0001671894,0.0002602357,0.001827561,0.0003066916,0.0008929551,0.000041319,0.00003230948],"category_scores_gemma":[0.000008990343,0.0002025308,0.00002040416,0.0005709344,0.000212884,0.0004861254,0.0008932892,0.0005773635,0.000009711226],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001886627,"about_ca_system_score_gemma":0.0001547765,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006653631,"about_ca_topic_score_gemma":0.00002606622,"domain_scores_codex":[0.9982734,0.0001579329,0.0004769338,0.0004828513,0.0003788137,0.0002300323],"domain_scores_gemma":[0.9984781,0.0001182962,0.0003905073,0.0008153372,0.0001137232,0.00008404811],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002329378,0.0002284502,0.002270754,0.0000750825,0.00002919802,0.000001320646,0.005563181,0.44309,0.004164214,0.01248712,0.00001017465,0.5320572],"study_design_scores_gemma":[0.0005419221,0.0001462448,0.004136823,0.00002855142,0.00001845032,0.00001724501,0.003358521,0.9830806,0.000173134,0.000271253,0.007976592,0.0002506455],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002433132,0.0007042895,0.9946866,0.000810327,0.00001049904,0.0007570623,0.00000220185,0.00009196537,0.0005039439],"genre_scores_gemma":[0.9816865,0.0005134849,0.01440854,0.0001079478,0.000005905039,0.002420731,0.00008426453,0.00001570204,0.0007569087],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.980278,"threshold_uncertainty_score":0.9994719,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03048400050106643,"score_gpt":0.2569068097743107,"score_spread":0.2264228092732443,"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."}}