{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008654973,0.0001065433,0.0001952395,0.0003115757,0.0001624423,0.0002986924,0.000883747,0.00006092309,0.0001134299],"category_scores_gemma":[0.002153913,0.00007591095,0.0000812959,0.001708683,0.0001465893,0.0004076797,0.0002074724,0.0002160527,0.00005141734],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005540172,"about_ca_system_score_gemma":0.00006171956,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006973345,"about_ca_topic_score_gemma":0.00001662121,"domain_scores_codex":[0.9980296,0.00002489352,0.0008152422,0.0003719333,0.0006061343,0.0001521729],"domain_scores_gemma":[0.9983995,0.0003482211,0.000378966,0.0002411974,0.0006065955,0.00002553656],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00004160375,0.00004542467,0.005172788,0.000004314661,0.000003225973,4.055727e-8,0.0003321583,0.02375255,0.01459966,0.9242581,0.000165495,0.03162466],"study_design_scores_gemma":[0.00002424243,0.00004690988,0.002831376,0.0001274397,0.000005060521,1.874589e-7,0.001821718,0.2015831,0.1891748,0.6039189,0.0003790256,0.0000872649],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6881,0.00001325622,0.2081174,0.01026195,0.0003029999,0.001181428,0.000002973678,0.00009266721,0.09192727],"genre_scores_gemma":[0.9950293,0.00002422862,0.0004674771,0.0001200175,0.00001810019,0.00005923293,8.550162e-7,0.00000401587,0.004276818],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3203392,"threshold_uncertainty_score":0.3095559,"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."}}