{"id":"W3012286460","doi":"10.65109/lvjf2437","title":"Leveraging Communication Topologies Between Learning Agents in Deep Reinforcement Learning","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Network topology; Computer science; Reinforcement learning; Artificial intelligence; Machine learning; Benchmark (surveying); Distributed computing; Topology (electrical circuits); Theoretical computer science; Mathematics; Computer network","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003876966,0.0002992793,0.0005446746,0.0001746975,0.0001931627,0.0001558946,0.0006615471,0.0001057937,0.0008671971],"category_scores_gemma":[0.00002478679,0.0003257498,0.0002084748,0.0002065398,0.00004320486,0.00007648077,0.002708358,0.001970829,0.00002903915],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001365386,"about_ca_system_score_gemma":0.00004106983,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002671841,"about_ca_topic_score_gemma":0.00002254513,"domain_scores_codex":[0.9981241,0.0003251708,0.0005849599,0.0004444602,0.000215277,0.0003060567],"domain_scores_gemma":[0.9988149,0.0001638391,0.0003970633,0.0005102313,0.00005452363,0.00005937362],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000004083825,0.00001622943,0.6167932,0.0000287517,0.0002148145,9.653223e-7,0.001573499,0.3537863,0.00001091897,0.003272601,0.0004450444,0.02385354],"study_design_scores_gemma":[0.0007380288,0.0001007436,0.07504467,0.0006909535,0.0003346098,1.797616e-7,0.006979928,0.8007641,0.0009974273,0.09042191,0.0221946,0.001732863],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1638149,0.0002885544,0.7382939,0.001155496,0.00005646267,0.0006882249,8.702455e-7,0.0007280165,0.09497359],"genre_scores_gemma":[0.9948359,0.0001078916,0.00324079,0.00003617927,0.0001740797,0.00008412455,0.0008044444,0.00003026373,0.0006863044],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.831021,"threshold_uncertainty_score":0.9999195,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07488800774223038,"score_gpt":0.3339669271243948,"score_spread":0.2590789193821644,"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."}}