{"id":"W1037351197","doi":"10.1613/jair.4676","title":"Approximate Value Iteration with Temporally Extended Actions","year":2015,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Research","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; European Commission","keywords":"Landmark; Computer science; Convergence (economics); Bellman equation; Mathematical optimization; Reinforcement learning; Value (mathematics); Function (biology); Term (time); State space; Mathematics; Artificial intelligence; Machine learning; Statistics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.004761231,0.0001144486,0.0001872685,0.0005817218,0.0002310636,0.0007168989,0.001076493,0.00006657666,0.00001692381],"category_scores_gemma":[0.0007684708,0.00008539605,0.00006247008,0.001165231,0.0001700007,0.001377141,0.0001688524,0.0007882146,0.0001069165],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002158679,"about_ca_system_score_gemma":0.0008286922,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002482724,"about_ca_topic_score_gemma":0.000005977709,"domain_scores_codex":[0.9965006,0.0003703913,0.0006449328,0.0002041585,0.001859363,0.0004205733],"domain_scores_gemma":[0.9963797,0.0002477662,0.000311702,0.0004032837,0.002350853,0.0003067105],"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":[0.000189924,0.0001830411,0.0001290981,0.00001576704,0.00004868655,0.0001390876,0.003012781,0.7680834,0.002802607,0.1740106,0.00100064,0.05038434],"study_design_scores_gemma":[0.00008520187,0.002237396,0.00005234099,0.0001020796,0.000007577873,0.0002406701,0.001833583,0.9334717,0.02851975,0.03039762,0.002877169,0.0001748637],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00588956,0.00004413497,0.9890772,0.00234292,0.0003474538,0.0001678109,2.076644e-7,0.00002975476,0.002101019],"genre_scores_gemma":[0.8755842,0.00003247348,0.12358,0.00005334305,0.0003195096,0.000005194316,8.103513e-7,0.00001405908,0.0004104108],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8696947,"threshold_uncertainty_score":0.6913072,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3129026095091614,"score_gpt":0.4403874809011682,"score_spread":0.1274848713920068,"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."}}