{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008131469,0.0005406288,0.0005249988,0.0002387326,0.0003274167,0.0006589564,0.00302319,0.0004867802,0.0001454184],"category_scores_gemma":[0.0003081581,0.0005122465,0.0002229262,0.0004004455,0.00005729552,0.0004698291,0.005486461,0.001350356,0.0007173102],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002339195,"about_ca_system_score_gemma":0.0002408525,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001452135,"about_ca_topic_score_gemma":0.000001020307,"domain_scores_codex":[0.9961724,0.0002941829,0.0007270779,0.001159286,0.0009509927,0.0006960087],"domain_scores_gemma":[0.997296,0.00007420982,0.0007103662,0.001370506,0.0003403273,0.0002086284],"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":[0.000002467612,0.00005218138,0.02308041,0.0002044912,0.0001726999,0.00002730727,0.0005324146,0.792652,0.0001038232,0.0006938825,0.1815672,0.0009111362],"study_design_scores_gemma":[0.0002234246,0.0001058228,0.0003706137,0.0003577795,0.00001667167,0.00000947428,0.00003323818,0.9824073,0.0001950173,0.0002167252,0.01541492,0.0006489964],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005327521,0.00008980316,0.968842,0.0003952446,0.002216796,0.0004665089,0.000001930111,0.006043588,0.01661662],"genre_scores_gemma":[0.760808,0.00008307787,0.2090539,0.0003973698,0.000388559,0.00006648479,0.000314253,0.000116426,0.02877197],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7597881,"threshold_uncertainty_score":0.9997329,"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."}}