{"id":"W3194439889","doi":"10.2139/ssrn.3910498","title":"Robust Risk-Aware Reinforcement Learning","year":2021,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Risk and Portfolio Optimization","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Reinforcement learning; Reinforcement; Computer science; Artificial intelligence; Psychology; Social psychology","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":[0.006296268,0.000132513,0.0002070774,0.0001868649,0.0006166932,0.0003771549,0.0003952259,0.00007834414,0.0006884672],"category_scores_gemma":[0.001682936,0.0001022659,0.0001775688,0.0007554364,0.00002664454,0.0003995865,0.00007738017,0.001990877,0.0003183269],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003725399,"about_ca_system_score_gemma":0.002511926,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003419539,"about_ca_topic_score_gemma":0.0003652815,"domain_scores_codex":[0.9960585,0.0003897732,0.0006207728,0.0003014332,0.001146268,0.001483255],"domain_scores_gemma":[0.99827,0.0002066105,0.0005264563,0.0002905986,0.0005847757,0.000121522],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00002830294,0.00002496854,0.02957073,4.180789e-7,0.00006861359,0.0000212154,0.000243705,0.8084737,0.00002486849,0.01735802,0.001367434,0.142818],"study_design_scores_gemma":[0.002387322,0.0007928564,0.005225779,0.00003679638,0.0001447132,0.00269191,0.02451791,0.1841932,0.0006664983,0.5491019,0.2294114,0.0008296862],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08033089,0.002996626,0.9051356,0.0009412238,0.0005750377,0.00007610138,9.888603e-7,0.00004346438,0.009900077],"genre_scores_gemma":[0.9239062,0.03294053,0.0004197744,0.00008146454,0.0003123586,0.00000174887,0.000008622963,0.00001560651,0.04231367],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9047158,"threshold_uncertainty_score":0.8649479,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04207220615069272,"score_gpt":0.312367694612759,"score_spread":0.2702954884620662,"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."}}