{"id":"W4393161074","doi":"10.1609/aaai.v38i19.30101","title":"Solving Non-rectangular Reward-Robust MDPs via Frequency Regularization","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Advanced Adaptive Filtering Techniques","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Regularization (linguistics); Computer science; Mathematical optimization; Mathematics; Applied mathematics; Artificial intelligence","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":[0.001429458,0.0008671887,0.001003067,0.0003975394,0.0003782502,0.0006721705,0.0008324307,0.001283098,0.001535604],"category_scores_gemma":[0.004854905,0.0005832276,0.0006729093,0.0002942911,0.001161376,0.0008895556,0.00141291,0.001516938,0.000177778],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001035565,"about_ca_system_score_gemma":0.001494222,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006538974,"about_ca_topic_score_gemma":0.004472563,"domain_scores_codex":[0.999551,0.000171127,0.00002156444,0.0001057506,0.00007317265,0.00007731873],"domain_scores_gemma":[0.9974722,0.002005162,0.0002166201,0.0001073517,0.0001099198,0.00008865399],"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":[0.00002532391,0.00001316587,0.0002041587,0.00002088889,0.00001233328,0.00002776634,0.00002085653,0.9879556,0.0003620196,0.006920351,0.0001953752,0.004242264],"study_design_scores_gemma":[0.000004508424,0.000009154123,0.00002475258,0.000002268708,0.000001809548,0.000004075322,0.000003536921,0.9971106,0.00008674073,0.002678968,0.00007177911,0.000001758319],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0412536,0.0001785122,0.9555926,0.0003067371,0.0000250077,0.00004895648,0.00004274,0.0002560534,0.002295827],"genre_scores_gemma":[0.8715516,0.0001575184,0.1253236,0.0001873405,0.00003491611,0.0001889034,0.00008910199,0.000112257,0.002354737],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006538974,"threshold_uncertainty_score":0.01300186,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04416407608534164,"score_gpt":0.2634541752053656,"score_spread":0.2192900991200239,"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."}}