{"id":"W2970384648","doi":"10.48550/arxiv.1912.04226","title":"Unsupervised Curricula for Visual Meta-Reinforcement Learning","year":2019,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Reinforcement learning; Unsupervised learning; Artificial intelligence; Machine learning; Meta learning (computer science); Cluster analysis; Task (project management); Discriminative model; Trajectory","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":[],"consensus_categories":[],"category_scores_codex":[0.0003213865,0.0002433777,0.0003228617,0.0001828021,0.0002028022,0.0001124839,0.0009922818,0.00008993108,0.0002182426],"category_scores_gemma":[0.00004977913,0.0002407098,0.0003306157,0.0006067531,0.00004196821,0.0007799964,0.0003856779,0.0002169627,0.0004991085],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001102045,"about_ca_system_score_gemma":0.0000609181,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001672975,"about_ca_topic_score_gemma":8.805177e-7,"domain_scores_codex":[0.9984559,0.00008172745,0.0002145672,0.0006281437,0.0001476098,0.0004720437],"domain_scores_gemma":[0.998769,0.0001988647,0.000173464,0.0005575621,0.0001607982,0.0001403355],"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":[0.00001380323,0.00001875044,0.002225755,0.00002366011,0.000227525,0.0000101695,0.00009056766,0.8944921,0.0001276085,0.1025479,0.000082529,0.0001396574],"study_design_scores_gemma":[0.0009814192,0.0003460206,0.0001745254,0.00001121495,0.0001932652,0.000001839637,0.00006646811,0.9907917,0.000294539,0.0003302259,0.006497884,0.0003109459],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05299733,0.00001866848,0.9421731,0.0000520164,0.000276146,0.0004774333,3.416927e-7,0.0002531407,0.003751806],"genre_scores_gemma":[0.9816253,0.0000176957,0.002330003,0.0001653005,0.00002973594,0.000002471734,0.00001083623,0.00001737381,0.01580126],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9398431,"threshold_uncertainty_score":0.981586,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06914127001221135,"score_gpt":0.2036564058526367,"score_spread":0.1345151358404253,"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."}}