{"id":"W4393159648","doi":"10.1609/aaai.v38i14.29524","title":"PORTAL: Automatic Curricula Generation for Multiagent Reinforcement Learning","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Multi-Agent Systems and Negotiation","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs; University of Alberta; Alberta Machine Intelligence Institute; Compute Canada; National Natural Science Foundation of China; Canadian Institute for Advanced Research","keywords":"Curriculum; Reinforcement learning; Computer science; Artificial intelligence; Psychology; Pedagogy","routes":{"ca_aff":true,"ca_fund":true,"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":[0.002033616,0.0008146049,0.0008935367,0.0005291057,0.000470581,0.0007992751,0.002142698,0.001136325,0.007333459],"category_scores_gemma":[0.005406728,0.000483874,0.0005062497,0.0003255025,0.0007144228,0.001278345,0.002029531,0.001770225,0.001479346],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008786513,"about_ca_system_score_gemma":0.00162519,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002930207,"about_ca_topic_score_gemma":0.003123252,"domain_scores_codex":[0.9993417,0.000285203,0.00003379057,0.0001352785,0.0001358468,0.0000682138],"domain_scores_gemma":[0.9987575,0.0006596546,0.000114641,0.0001653496,0.0001794644,0.0001234593],"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":[0.0003037154,0.0003727572,0.002010838,0.0002397299,0.00007752037,0.0001551467,0.0001943928,0.6612207,0.004239808,0.02500063,0.009159395,0.2970254],"study_design_scores_gemma":[0.00004100813,0.0000288405,0.00005431845,0.000004675954,0.000003219819,0.00001015814,0.000006063646,0.9939394,0.000583378,0.004239445,0.001085696,0.000003823316],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006817077,0.00009531248,0.9867747,0.0001143488,0.00004361697,0.0001212718,0.00006407215,0.004708738,0.001260896],"genre_scores_gemma":[0.3807248,0.0001186096,0.6143667,0.000190124,0.00004917323,0.0007364412,0.000365528,0.0004569864,0.002991743],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007333459,"threshold_uncertainty_score":0.02453285,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1040794135188012,"score_gpt":0.3231192467728909,"score_spread":0.2190398332540897,"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."}}