{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001376683,0.0007570144,0.001035402,0.0003525913,0.0004504879,0.0007041083,0.001011558,0.0007517494,0.0007292535],"category_scores_gemma":[0.004192484,0.0004006351,0.0004425314,0.0002409802,0.0008429857,0.001039847,0.001095207,0.001221356,0.0001198109],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008422963,"about_ca_system_score_gemma":0.001229703,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006557878,"about_ca_topic_score_gemma":0.004173995,"domain_scores_codex":[0.9990816,0.0003021517,0.00005064035,0.0002742091,0.0001646089,0.0001267703],"domain_scores_gemma":[0.9981218,0.001095723,0.0002845437,0.0001242972,0.0002330647,0.0001405972],"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":[0.0001963231,0.0001564775,0.002665889,0.00009099,0.00006889686,0.0001612745,0.0001287775,0.920797,0.003723815,0.006187644,0.0004604037,0.06536248],"study_design_scores_gemma":[0.00001233781,0.0000348369,0.0002003021,0.000002910192,0.000005632561,0.00001107824,0.000006903067,0.9976113,0.0004722637,0.001502468,0.0001348953,0.000005059783],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1029301,0.0006278277,0.8936676,0.0002549743,0.00007015385,0.00008933726,0.00003072655,0.0005834127,0.001745842],"genre_scores_gemma":[0.9478785,0.0001134442,0.05091111,0.00008546845,0.00001718427,0.00007551467,0.00002543081,0.00001954979,0.0008737837],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006557878,"threshold_uncertainty_score":0.01303941,"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."}}