{"id":"W3167724086","doi":"10.48550/arxiv.2106.00136","title":"Tesseract: Tensorised Actors for Multi-Agent Reinforcement Learning","year":2021,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Lattice Boltzmann Simulation Studies","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Toronto","funders":"European Commission; Nvidia","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Tensor (intrinsic definition); Bellman equation; Mathematical optimization; Function (biology); Machine learning; Mathematics; Pure mathematics","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":[0.00006557577,0.0001500108,0.0001666626,0.00007051766,0.0001659311,0.00002538219,0.00009869256,0.00006072895,0.00009241356],"category_scores_gemma":[0.00009336589,0.0001752502,0.0001027214,0.0002803586,0.00002175422,0.0002046187,0.00006158894,0.0001264244,0.00007414701],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001442323,"about_ca_system_score_gemma":0.00002075907,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004642755,"about_ca_topic_score_gemma":0.00001017698,"domain_scores_codex":[0.999298,0.00001851404,0.000135129,0.0002503158,0.00004770545,0.0002503677],"domain_scores_gemma":[0.9993744,0.0001355031,0.00004075231,0.0002004414,0.0001700707,0.0000788387],"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":[0.00001196055,0.00001871743,0.006396169,0.00004617995,0.0001172426,0.00003790804,0.0002454957,0.9898379,0.0009914985,0.001962287,0.0002177347,0.0001168399],"study_design_scores_gemma":[0.001307048,0.00002264983,0.004139537,0.00001945662,0.00008014559,9.759191e-7,0.0009059055,0.9719743,0.002787795,0.00006801878,0.01842763,0.0002665721],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6654835,0.00009600399,0.3302861,0.00002299486,0.0003605681,0.0002517514,0.000004806752,0.0004575232,0.00303671],"genre_scores_gemma":[0.9912444,0.0000989842,0.0006187911,0.00003160334,0.00004506062,0.000001437158,0.00001823335,0.00002816303,0.007913356],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3296673,"threshold_uncertainty_score":0.7146497,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1030873107217989,"score_gpt":0.2113070256071444,"score_spread":0.1082197148853454,"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."}}