{"id":"W7133070489","doi":"","title":"Optimizing Mechanism Design in Multi-Agent Reinforcement Learning","year":2024,"lang":"","type":"dissertation","venue":"TSpace","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Agencia Nacional de Investigación y Desarrollo; University of Toronto","keywords":"Reinforcement learning; Mechanism design; Markov decision process; Bridging (networking); Benchmark (surveying); Robustness (evolution); Mechanism (biology); Nash equilibrium","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005653471,0.001321407,0.001770059,0.0008209035,0.0005333758,0.001653495,0.00180861,0.001830667,0.002183764],"category_scores_gemma":[0.01294007,0.0007658019,0.0009086598,0.0007121358,0.002137292,0.001844143,0.001454609,0.002378756,0.0002799007],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002298355,"about_ca_system_score_gemma":0.002324122,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002681968,"about_ca_topic_score_gemma":0.002064918,"domain_scores_codex":[0.9973674,0.001592396,0.0001196063,0.0003655884,0.0003431248,0.0002119009],"domain_scores_gemma":[0.992292,0.00606899,0.0006138316,0.0003147914,0.0004835382,0.0002268973],"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":[0.00003703237,0.00004985711,0.0003670094,0.00008801265,0.00005054811,0.00003921283,0.00004683459,0.9297471,0.0003305964,0.05928696,0.0003401306,0.009616683],"study_design_scores_gemma":[0.00003152926,0.00002899987,0.00003330014,0.00001007862,0.000008252579,0.000006571309,0.000006193789,0.971798,0.0001292187,0.02757348,0.0003693143,0.000004967338],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01530089,0.0005270464,0.9806113,0.0004968474,0.00004307159,0.0001315337,0.00003898924,0.0001783537,0.00267194],"genre_scores_gemma":[0.8052276,0.0007488985,0.1894114,0.0002883834,0.00006553518,0.0007972554,0.00009042992,0.0000701728,0.003300397],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005653471,"threshold_uncertainty_score":0.02989876,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06547687145312808,"score_gpt":0.3433784059699186,"score_spread":0.2779015345167905,"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."}}