{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009585557,0.0003649227,0.0004877408,0.001600619,0.0002653188,0.0002482792,0.001400157,0.0003014471,0.00001551004],"category_scores_gemma":[0.0002850447,0.0003607639,0.0001546896,0.001043692,0.000472019,0.0009926512,0.0004778915,0.0004069376,0.000005192956],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004106039,"about_ca_system_score_gemma":0.0005397045,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001040328,"about_ca_topic_score_gemma":0.000003207729,"domain_scores_codex":[0.9970983,0.00003275291,0.0007612702,0.0007076273,0.0009152218,0.000484787],"domain_scores_gemma":[0.9967464,0.0007749382,0.0009063795,0.0009502696,0.0005085315,0.000113497],"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":[0.000001952534,0.00001127406,0.0001027149,0.00007563243,0.00001339243,9.839949e-7,0.0001978824,0.6930733,0.0001843884,0.0172803,0.000001482094,0.2890567],"study_design_scores_gemma":[0.0002250344,0.0001227853,0.0001350535,0.0002232182,0.00002815133,0.0000326487,2.922074e-7,0.9730136,0.0009607902,0.02467792,0.0002380359,0.0003424367],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000256249,0.0001467788,0.9962052,0.00007869527,0.002184525,0.0006461242,0.000003535018,0.0001369382,0.0003420202],"genre_scores_gemma":[0.1991293,0.00001228006,0.8005054,0.00007299622,0.0001949211,0.00000433877,0.00000625824,0.00002388882,0.00005060498],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2887143,"threshold_uncertainty_score":0.9998844,"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."}}