{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001354021,0.0009093371,0.0007218548,0.0004626646,0.0004831971,0.0008855378,0.001964422,0.001030977,0.003217113],"category_scores_gemma":[0.007063257,0.0005642539,0.0006060272,0.0003804174,0.001380664,0.001804248,0.001967232,0.002011597,0.0006741236],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001360805,"about_ca_system_score_gemma":0.001444407,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001636474,"about_ca_topic_score_gemma":0.003212903,"domain_scores_codex":[0.9994137,0.0002227507,0.0000302063,0.0001705623,0.00009849423,0.00006422414],"domain_scores_gemma":[0.9979084,0.001097815,0.0001962396,0.0004010027,0.0002470426,0.0001494644],"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":[0.0001295171,0.0001969939,0.001822203,0.0001572946,0.00006805388,0.00006256158,0.0002683374,0.7790239,0.004647855,0.07087,0.001996446,0.1407568],"study_design_scores_gemma":[0.00001901465,0.00003920043,0.0001256772,0.00001334023,0.000005690446,0.0000107602,0.00001125953,0.9672233,0.001053072,0.03065896,0.000833283,0.000006398855],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0176579,0.0001272085,0.9791834,0.0002299393,0.00002013487,0.00007646219,0.0000558215,0.0005882589,0.002060992],"genre_scores_gemma":[0.6907538,0.0001778345,0.3036217,0.0002094781,0.00004154679,0.0005668413,0.0002221867,0.0002096283,0.004196979],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003217113,"threshold_uncertainty_score":0.01076227,"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."}}