{"id":"W2785529341","doi":"10.1609/aaai.v32i1.12115","title":"Learning Robust Options","year":2018,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Robustness (evolution); Reinforcement learning; Computer science; Artificial intelligence; Robust control; Mathematical optimization; Machine learning; Convergence (economics); Artificial neural network; Mathematics; Nonlinear system","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":[0.0005351925,0.0001943527,0.0001900426,0.0001393413,0.0004487199,0.0003565536,0.002349671,0.00008458081,0.0001474846],"category_scores_gemma":[0.0006924099,0.0001509401,0.0001020011,0.0008133183,0.0004666946,0.0004816156,0.0005800494,0.0004300427,0.0004858063],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000046063,"about_ca_system_score_gemma":0.00008280168,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001599964,"about_ca_topic_score_gemma":0.000002794937,"domain_scores_codex":[0.9981686,0.00002197638,0.0004713399,0.0004221885,0.0005373764,0.0003784852],"domain_scores_gemma":[0.9981746,0.00008199643,0.0003903506,0.0003300728,0.0009378651,0.00008510109],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000139182,0.00003911988,0.0002612524,0.0000132093,0.00001179743,1.84315e-7,0.001294448,0.02105871,0.01064672,0.9502605,0.0001778029,0.01622231],"study_design_scores_gemma":[0.00002138297,0.0005521205,0.0002208501,0.0001644001,0.0000101452,0.000005008787,0.0004898432,0.7444569,0.2190859,0.03412538,0.0006282575,0.0002397504],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03304217,0.000009361038,0.8841439,0.003691172,0.0009435476,0.0003795862,6.850854e-7,0.0002914316,0.07749815],"genre_scores_gemma":[0.9830374,0.00002175085,0.01476548,0.0001603324,0.0001418808,0.00001151946,2.488612e-7,0.00001240449,0.001848945],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9499953,"threshold_uncertainty_score":0.6244219,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09360344398562903,"score_gpt":0.2975536324951889,"score_spread":0.2039501885095599,"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."}}