{"id":"W3126457215","doi":"10.1007/s00521-023-09096-6","title":"hammer: Multi-level coordination of reinforcement learning agents via learned messaging","year":2023,"lang":"en","type":"article","venue":"Neural Computing and Applications","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Representation (politics); Artificial intelligence; Information sharing; Distributed computing; Artificial neural network; Embodied agent; Human–computer interaction; Machine learning; Embodied cognition; World Wide Web","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":[0.001228189,0.0007706011,0.0009740805,0.0004944507,0.0006470205,0.001272656,0.002196142,0.001495831,0.009532152],"category_scores_gemma":[0.004531578,0.0005292646,0.0004205716,0.0003503766,0.0009782531,0.001679261,0.002727699,0.001912772,0.001485123],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006421304,"about_ca_system_score_gemma":0.0009376375,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002092085,"about_ca_topic_score_gemma":0.002718061,"domain_scores_codex":[0.9993176,0.0001865481,0.00004651612,0.0001657022,0.0001770014,0.0001066669],"domain_scores_gemma":[0.9983293,0.0008405416,0.000126344,0.0003234046,0.0001751898,0.000205157],"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":[0.0008840659,0.0003032499,0.0008995222,0.0002046918,0.0001173988,0.0003922284,0.0002617419,0.7424741,0.0174996,0.06706534,0.008903055,0.1609951],"study_design_scores_gemma":[0.0000593875,0.00005343385,0.00005575653,0.000006318383,0.000007856309,0.00001920319,0.0000136845,0.9809843,0.002203637,0.01532257,0.001265375,0.000008452737],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01845583,0.0001198398,0.9689543,0.0002569068,0.0001770859,0.0001217975,0.00007282694,0.00603671,0.005804879],"genre_scores_gemma":[0.788222,0.00009051973,0.1995144,0.0001761709,0.00006355382,0.0002761304,0.000140827,0.0003931642,0.01112318],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009532152,"threshold_uncertainty_score":0.03188825,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07241711314584617,"score_gpt":0.3268099406411876,"score_spread":0.2543928274953414,"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."}}