{"id":"W2791696004","doi":"10.1109/cig.2018.8490448","title":"Automated Curriculum Learning by Rewarding Temporally Rare Events","year":2018,"lang":"en","type":"preprint","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"York University","keywords":"Reinforcement learning; Computer science; Event (particle physics); Function (biology); Simple (philosophy); Artificial intelligence; Human–computer interaction; Machine learning; Cognitive psychology; Psychology","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001059574,0.0005743352,0.0006175269,0.000300641,0.0003236549,0.0007506433,0.001045002,0.0006560751,0.002826474],"category_scores_gemma":[0.007248548,0.0003216613,0.0003145009,0.0002222283,0.0009035824,0.0013687,0.001508244,0.001287313,0.0004697552],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005396776,"about_ca_system_score_gemma":0.0007771712,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006613983,"about_ca_topic_score_gemma":0.001202377,"domain_scores_codex":[0.9994714,0.0001803606,0.00002929422,0.0001462291,0.00009542506,0.00007736399],"domain_scores_gemma":[0.9970714,0.001503011,0.0004513921,0.0004890152,0.0002129044,0.0002722457],"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":[0.0005400452,0.0003545568,0.005675492,0.0002095346,0.00007727854,0.0002167971,0.0002274511,0.7205805,0.02977279,0.04725147,0.002156924,0.1929372],"study_design_scores_gemma":[0.00004657606,0.000105311,0.0004736901,0.0000113984,0.00001127918,0.00004026819,0.000012893,0.9744862,0.006034588,0.01753391,0.001229542,0.00001440971],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1500691,0.0002034916,0.8425165,0.0003346264,0.00006027892,0.0001089264,0.00007955922,0.001583846,0.005043657],"genre_scores_gemma":[0.9201692,0.00008540311,0.07716703,0.00007933396,0.00002278862,0.00009085645,0.00006794911,0.00007935651,0.002238029],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002826474,"threshold_uncertainty_score":0.009455502,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01408645563286042,"score_gpt":0.2715538308190012,"score_spread":0.2574673751861408,"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."}}