{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003967328,0.001460587,0.00177015,0.0009826598,0.0006775125,0.001517744,0.00190805,0.001530422,0.004467854],"category_scores_gemma":[0.01238616,0.0009678878,0.001265017,0.00133825,0.001588983,0.002371422,0.002125025,0.004364605,0.0007516555],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002426562,"about_ca_system_score_gemma":0.002264733,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005434577,"about_ca_topic_score_gemma":0.007759475,"domain_scores_codex":[0.998148,0.0008825773,0.00007974262,0.0002066485,0.0004858345,0.0001972448],"domain_scores_gemma":[0.9926267,0.006054264,0.0003441585,0.0004450205,0.0004020594,0.0001278387],"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":[0.00004761458,0.00006166828,0.0003300435,0.0001143004,0.00003056795,0.00002988477,0.00008914666,0.8942477,0.0004196487,0.06275066,0.001113792,0.0407649],"study_design_scores_gemma":[0.000009218928,0.00001254421,0.00001859164,0.00001150896,0.000003880949,0.000006949772,0.00000918353,0.9726583,0.0002052144,0.02668919,0.0003724779,0.000002816007],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00432443,0.0002359649,0.9931385,0.0001903331,0.00001435133,0.00003648844,0.00002793656,0.0002320653,0.001799887],"genre_scores_gemma":[0.3450527,0.0006002193,0.6498432,0.00023501,0.000069179,0.0004517939,0.0001849443,0.000309117,0.003253884],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005434577,"threshold_uncertainty_score":0.02098149,"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."}}