{"id":"W1433129784","doi":"10.1007/978-3-642-29946-9_16","title":"Automatic Construction of Temporally Extended Actions for MDPs Using Bisimulation Metrics","year":2012,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"","keywords":"Markov decision process; Reinforcement learning; Computer science; Bisimulation; Metric (unit); Set (abstract data type); Markov process; Process (computing); Q-learning; Performance metric; Artificial intelligence; Theoretical computer science; Mathematical optimization; Algorithm; Mathematics; Programming language","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":[0.002000354,0.001675579,0.001862323,0.001647455,0.0008760456,0.001329285,0.001914867,0.001511326,0.005420651],"category_scores_gemma":[0.009132884,0.001491683,0.002256344,0.001007452,0.001642358,0.00275642,0.005075929,0.003022277,0.0009572136],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001691978,"about_ca_system_score_gemma":0.002200911,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001835565,"about_ca_topic_score_gemma":0.00333565,"domain_scores_codex":[0.9984316,0.0004201998,0.0001501877,0.0003252842,0.0005383584,0.0001343685],"domain_scores_gemma":[0.9955051,0.002855134,0.0002943236,0.0005073367,0.0006021129,0.0002359991],"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":[0.0002367577,0.0001420891,0.0006758812,0.0004970961,0.00008049885,0.0002195661,0.0003024094,0.6377551,0.01490714,0.1494801,0.002026279,0.193677],"study_design_scores_gemma":[0.00001861118,0.00005250212,0.00006720537,0.0000347626,0.00001187148,0.00002772595,0.00002534802,0.9311885,0.003192473,0.06412603,0.001243031,0.00001189256],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01004821,0.00007058235,0.9878774,0.00004749443,0.00002374329,0.00008316277,0.00007807816,0.0007393487,0.001031973],"genre_scores_gemma":[0.1703945,0.0001549313,0.8264566,0.00005015255,0.00002226219,0.0004828405,0.000495542,0.0005401311,0.001403096],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005420651,"threshold_uncertainty_score":0.01813388,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05606483487029121,"score_gpt":0.3043537203516835,"score_spread":0.2482888854813923,"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."}}