{"id":"W7124301997","doi":"10.65109/tjqd1268","title":"PORTAL: Automatic Curricula Generation for Multiagent 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":"University of Alberta","funders":"","keywords":"Reinforcement learning; Task (project management); Curriculum; Feature (linguistics); Space (punctuation); Active learning (machine learning); Key (lock); Transfer of learning","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001885574,0.0005975485,0.0005217462,0.0005515502,0.001088318,0.001026663,0.001103908,0.0002465765,0.0007936009],"category_scores_gemma":[0.0007208987,0.0005957566,0.0004021754,0.001628498,0.00009514337,0.0009531162,0.0007887679,0.0004345946,0.002010398],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002151825,"about_ca_system_score_gemma":0.0002513413,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002817052,"about_ca_topic_score_gemma":0.000003587927,"domain_scores_codex":[0.994498,0.0001866852,0.001550226,0.001111658,0.001280298,0.001373122],"domain_scores_gemma":[0.9971176,0.0003060751,0.0007427464,0.001070893,0.0004241993,0.0003384982],"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":[0.000002810564,0.00002986942,0.0001846598,0.0001974919,0.0001029027,0.0000216853,0.001452095,0.9330119,0.0008133367,0.01161284,0.01764038,0.03493005],"study_design_scores_gemma":[0.001092055,0.0006799938,0.0002532306,0.0001430834,0.0000820239,0.00001050176,0.0002344499,0.9816387,0.001175262,0.00003606556,0.01393499,0.0007196179],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004094966,0.0000730368,0.9840531,0.0009218756,0.003434474,0.002192485,0.000001052364,0.001566283,0.00366274],"genre_scores_gemma":[0.8902926,0.0002563188,0.03951428,0.0004697924,0.0006549035,0.000345352,0.0003083753,0.00009145357,0.06806695],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9445388,"threshold_uncertainty_score":0.9996494,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05505160572722048,"score_gpt":0.3059342340578389,"score_spread":0.2508826283306185,"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."}}