{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001482036,0.0007804106,0.0007396149,0.0004576956,0.0007199744,0.001121666,0.00138982,0.001052751,0.002083777],"category_scores_gemma":[0.007797842,0.0005876802,0.0003071106,0.0004081058,0.001657061,0.002520599,0.002068131,0.0017325,0.0003976992],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007764032,"about_ca_system_score_gemma":0.0007844674,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00126768,"about_ca_topic_score_gemma":0.001779901,"domain_scores_codex":[0.9992711,0.0003308053,0.0000331734,0.0001318298,0.0001531249,0.0000800681],"domain_scores_gemma":[0.9971191,0.001655304,0.0004714588,0.0003220443,0.0002143537,0.0002179148],"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":[0.00008644116,0.00006192984,0.0007436186,0.00004727779,0.00002320839,0.0001021836,0.0001050792,0.9438061,0.00200441,0.02994554,0.0006115332,0.0224627],"study_design_scores_gemma":[0.00001783909,0.00005135947,0.00009162558,0.000006623904,0.000005608301,0.00002112352,0.00001831457,0.9737324,0.0004661301,0.02510848,0.0004743377,0.000006163662],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06089442,0.0003791273,0.9328582,0.0006406733,0.00008752682,0.00006224577,0.00004451917,0.0003886949,0.004644649],"genre_scores_gemma":[0.944303,0.000234185,0.05336718,0.0001403681,0.00005422178,0.000131589,0.00003421287,0.00004159295,0.00169363],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002083777,"threshold_uncertainty_score":0.007837892,"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."}}