{"id":"W4409348534","doi":"10.1609/aaai.v39i27.35100","title":"Representation-driven Option Discovery in Reinforcement Learning","year":2025,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Simulation Techniques and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Representation (politics); Computer science; Artificial intelligence; Machine learning; Data science; Political 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":[0.003107315,0.0006497527,0.00124244,0.0005691121,0.0005637785,0.001679777,0.001974921,0.00194302,0.003365717],"category_scores_gemma":[0.01213119,0.0006367004,0.0009428787,0.0007054301,0.002745181,0.003333003,0.002231022,0.002942939,0.0003252817],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001764049,"about_ca_system_score_gemma":0.001558112,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003463357,"about_ca_topic_score_gemma":0.002839424,"domain_scores_codex":[0.9984238,0.000799188,0.00007374168,0.0002567439,0.0002942511,0.0001522024],"domain_scores_gemma":[0.9951034,0.003658089,0.0003554735,0.0003186982,0.0003235213,0.0002408693],"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":[0.0001340644,0.00006087872,0.0007598539,0.0001067243,0.00006273256,0.0001355518,0.0002177452,0.6610442,0.000922925,0.3073489,0.001181715,0.02802459],"study_design_scores_gemma":[0.00002420053,0.00002628388,0.00004983639,0.00001218302,0.000008291368,0.00001708077,0.00001103712,0.8697261,0.0002511157,0.1292617,0.0006007808,0.00001150145],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02659862,0.0006501378,0.9645903,0.001032725,0.0000632485,0.00006300089,0.00008837465,0.0002415007,0.006671998],"genre_scores_gemma":[0.8280747,0.0005126409,0.1661414,0.0002812704,0.00007090365,0.0002382623,0.0001503524,0.00007855724,0.004451872],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003463357,"threshold_uncertainty_score":0.01643324,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.19708603073947,"score_gpt":0.4407234229514519,"score_spread":0.2436373922119819,"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."}}