{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003673363,0.000132103,0.0001565123,0.0001787249,0.0004489533,0.0000945825,0.0003944971,0.00004454948,0.000003288324],"category_scores_gemma":[0.00005352496,0.0001388019,0.00004624575,0.0007710133,0.00005125915,0.0001630321,0.0004146654,0.0002209701,0.00003440402],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001924268,"about_ca_system_score_gemma":0.00001693165,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002428833,"about_ca_topic_score_gemma":4.401308e-7,"domain_scores_codex":[0.9987166,0.00006146014,0.0003523018,0.0003325569,0.0002634271,0.0002736539],"domain_scores_gemma":[0.999101,0.0001608939,0.0002568111,0.0003038163,0.0001062786,0.00007114965],"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":[8.565068e-7,0.000009674683,0.001796367,0.00003449903,0.00001405138,5.18029e-7,0.000322388,0.9312744,0.001248482,0.005253341,0.00008775407,0.05995772],"study_design_scores_gemma":[0.000302832,0.0000398495,0.008993527,0.00002198149,0.000009649002,0.000003967132,0.00006214336,0.9869428,0.0003968534,0.00007967625,0.00301719,0.0001295087],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01014149,0.00002487858,0.9879625,0.0005636821,0.0000638088,0.0002772573,3.690288e-7,0.0003972786,0.0005687212],"genre_scores_gemma":[0.9876514,0.00001676873,0.0103403,0.00008166159,0.00003241827,0.00002101574,0.00002317771,0.00001243123,0.001820836],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9776222,"threshold_uncertainty_score":0.5660177,"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."}}