{"id":"W1530573725","doi":"10.48550/arxiv.1206.6879","title":"Practical Linear Value-approximation Techniques for First-order MDPs","year":2012,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Markov decision process; Computer science; Bellman equation; Mathematical optimization; Linear programming; Probabilistic logic; Set (abstract data type); Function (biology); Domain (mathematical analysis); Value (mathematics); Markov process; Order (exchange); Algorithm; Mathematics; Artificial intelligence; Machine learning","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":[0.0003924123,0.00013292,0.0001213157,0.0001145257,0.0002030832,0.00005302441,0.0004619773,0.0001074571,0.00001633742],"category_scores_gemma":[0.0002278655,0.0001436589,0.00007263045,0.0004801344,0.00005223856,0.00149192,0.0002186131,0.000152775,0.00009516149],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001019187,"about_ca_system_score_gemma":0.00005111517,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000777551,"about_ca_topic_score_gemma":8.888517e-7,"domain_scores_codex":[0.999051,0.00005479244,0.0001353504,0.0002993477,0.00008887346,0.000370621],"domain_scores_gemma":[0.9988718,0.0002402392,0.0001328881,0.0004769443,0.0001529343,0.0001251848],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001688722,0.00008335105,0.002390281,0.00003263271,0.00002523531,0.00000560319,0.0002046681,0.2160763,0.00004839124,0.7795788,0.001260317,0.0002775383],"study_design_scores_gemma":[0.0002440269,0.00009977334,0.0002283978,0.00001301873,0.00002527774,0.00000556232,0.00003111157,0.9795176,0.0009601673,0.001442701,0.01724145,0.0001909475],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002366747,0.000005321423,0.9936504,0.0003916332,0.0001985782,0.0003315111,6.693095e-7,0.0003330178,0.002722129],"genre_scores_gemma":[0.7291979,0.00001597222,0.2693243,0.0001436207,0.0001016914,0.00000201553,0.000004736857,0.00001115533,0.001198555],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7781361,"threshold_uncertainty_score":0.585824,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09509342492505367,"score_gpt":0.2397068174315979,"score_spread":0.1446133925065442,"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."}}