{"id":"W4409347538","doi":"10.1609/aaai.v39i20.35403","title":"Are Expressive Models Truly Necessary for Offline RL?","year":2025,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Multi-Agent Systems and Negotiation","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Computer science","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":[0.001668702,0.001152054,0.001300359,0.0002395502,0.0005055961,0.002422025,0.001673128,0.001595192,0.006387624],"category_scores_gemma":[0.01294494,0.000895477,0.0008170133,0.000377637,0.002002816,0.006431853,0.002431452,0.005500487,0.001860294],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007935219,"about_ca_system_score_gemma":0.001895925,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002595943,"about_ca_topic_score_gemma":0.003545925,"domain_scores_codex":[0.9988099,0.0003649839,0.000058271,0.0003096124,0.0003051724,0.000152084],"domain_scores_gemma":[0.9959589,0.00245014,0.0002524932,0.0009444635,0.0002067778,0.0001871962],"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":[0.0002929051,0.0001399544,0.001649655,0.0005111761,0.000130688,0.0003063737,0.0003611158,0.5712399,0.005454501,0.2894419,0.009889732,0.1205821],"study_design_scores_gemma":[0.00003146113,0.00004451166,0.0001506932,0.00005245665,0.00001940243,0.00005568857,0.00005134373,0.7810327,0.001234429,0.2120326,0.005277164,0.00001756307],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01202793,0.0007226095,0.9754645,0.002301923,0.0001759357,0.00005476051,0.0003718118,0.001095206,0.007785401],"genre_scores_gemma":[0.7453246,0.001557484,0.2415183,0.001419183,0.0003169171,0.000381598,0.0009707717,0.0007340992,0.00777712],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006387624,"threshold_uncertainty_score":0.02136874,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1235148625104317,"score_gpt":0.3232024866937243,"score_spread":0.1996876241832926,"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."}}