{"id":"W4393146382","doi":"10.1609/aaai.v38i20.30613","title":"Reward-Respecting Subtasks for Model-Based Reinforcement Learning (Abstract Reprint)","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta; Canadian Institute for Advanced Research","funders":"","keywords":"Reprint; Reinforcement learning; Reinforcement; Psychology; Computer science; Artificial intelligence; Social psychology; Physics","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":[0.001165389,0.001174781,0.000871491,0.0003054462,0.0004571484,0.001008962,0.001222663,0.001206673,0.007889611],"category_scores_gemma":[0.0041791,0.000440855,0.000800336,0.0004530362,0.00133463,0.001403889,0.001812616,0.00268517,0.001217395],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001338248,"about_ca_system_score_gemma":0.001207573,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004716786,"about_ca_topic_score_gemma":0.004556787,"domain_scores_codex":[0.9994881,0.000215106,0.00002821547,0.0001057034,0.00009991677,0.0000627893],"domain_scores_gemma":[0.9988419,0.0007322283,0.00008983675,0.0001486843,0.00008796524,0.00009934931],"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":[0.0001496795,0.00008813665,0.0003641271,0.00009931136,0.00002936593,0.0001051202,0.00007057498,0.8579059,0.001622333,0.08279026,0.004720279,0.05205501],"study_design_scores_gemma":[0.00001125808,0.00001706006,0.00003061344,0.000008486909,0.000003502707,0.000006872921,0.000002318462,0.9533345,0.0002507046,0.04565765,0.000672573,0.000004485494],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0069101,0.0002607348,0.9882515,0.0003263757,0.00007956726,0.00004110163,0.00007991616,0.0007666259,0.003284058],"genre_scores_gemma":[0.6709624,0.0004904431,0.3191465,0.0004093279,0.0001441397,0.0004868962,0.0004316566,0.0004436454,0.007485004],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007889611,"threshold_uncertainty_score":0.02639335,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1002086969293765,"score_gpt":0.3268577768747262,"score_spread":0.2266490799453497,"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."}}