{"id":"W7124313799","doi":"10.65109/vmil8420","title":"Off-the-Grid MARL: Datasets and Baselines for Offline Multi-Agent Reinforcement Learning","year":2023,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Reinforcement learning; Bespoke; Online and offline; Measure (data warehouse); Power (physics)","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":[0.01143332,0.002486205,0.001694315,0.002472524,0.001205664,0.003478827,0.007778214,0.003320813,0.00689829],"category_scores_gemma":[0.06240484,0.00112698,0.001796381,0.002428249,0.002417879,0.005981507,0.005806569,0.005259415,0.006048348],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002227413,"about_ca_system_score_gemma":0.002829957,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006757985,"about_ca_topic_score_gemma":0.01115898,"domain_scores_codex":[0.9928365,0.003333983,0.0004653941,0.001312064,0.001645212,0.0004068083],"domain_scores_gemma":[0.9709036,0.01002012,0.001237305,0.0129297,0.003787196,0.001122119],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","study_design_scores_codex":[0.002202051,0.002301499,0.008945921,0.001854006,0.0004917233,0.0003291199,0.0002589384,0.5464016,0.002513391,0.02894578,0.174428,0.231328],"study_design_scores_gemma":[0.0003414238,0.0003810198,0.001661461,0.0001943094,0.0000411501,0.0001340795,0.0001195117,0.9288979,0.00341544,0.03586601,0.02888078,0.00006697608],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"dataset","genre_scores_codex":[0.08855102,0.006309569,0.701845,0.006235448,0.002197294,0.002007043,0.05546823,0.1104659,0.02692037],"genre_scores_gemma":[0.3393011,0.001114232,0.5276157,0.001494367,0.0002655178,0.002289345,0.1172884,0.006467701,0.004163658],"genre_candidate":"dataset","genre_consensus":null,"teacher_disagreement_score":0.01143332,"threshold_uncertainty_score":0.06046587,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05639460265554716,"score_gpt":0.3100390074822671,"score_spread":0.2536444048267199,"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."}}