{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006379609,0.0001807809,0.0001859865,0.0001331553,0.0002182218,0.0004496615,0.0007140978,0.00006843211,0.00005720017],"category_scores_gemma":[0.0002330187,0.0001301272,0.0001472111,0.0003850342,0.00005102096,0.0004758847,0.0001336094,0.0001637038,0.00007010644],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005640283,"about_ca_system_score_gemma":0.00006802732,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002464793,"about_ca_topic_score_gemma":0.000004422779,"domain_scores_codex":[0.9982659,0.00001501418,0.0005969827,0.0004415734,0.0004325006,0.0002479861],"domain_scores_gemma":[0.9990441,0.00006687887,0.0002770939,0.0001816233,0.0003706474,0.00005968776],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00000472077,0.00004981837,0.00003337068,0.0001966181,0.00002177003,4.580756e-7,0.001913711,0.002770656,0.08479757,0.8080168,0.0006507931,0.1015437],"study_design_scores_gemma":[0.00001648735,0.0001079872,0.00002508393,0.0002972878,0.00001168489,0.000002564168,0.0001352593,0.7889348,0.2055591,0.004426316,0.0003587619,0.0001247028],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.107326,0.000108254,0.8838519,0.002203873,0.002085872,0.001525043,0.00000256633,0.0003614283,0.002535042],"genre_scores_gemma":[0.995667,0.00002569072,0.003374446,0.00006380812,0.0001589374,0.0001175909,0.000002691979,0.00001263911,0.0005771751],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8883411,"threshold_uncertainty_score":0.5306435,"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."}}