{"id":"W1876478031","doi":"10.48550/arxiv.1206.3233","title":"Speeding Up Planning in Markov Decision Processes via Automatically Constructed Abstractions","year":2012,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Mathematical optimization; Markov decision process; Solver; Hierarchy; Decision problem; Focus (optics); State space; Shortest path problem; State (computer science); Markov chain; Markov process; Theoretical computer science; Algorithm; Mathematics; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003259485,0.0003003906,0.0003319777,0.0004054913,0.0001509977,0.0002011851,0.001269094,0.0003551545,0.0000517454],"category_scores_gemma":[0.000128553,0.0003438247,0.00008543703,0.0007114948,0.00009388938,0.0007137919,0.00100434,0.0008530071,0.00008950648],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001853679,"about_ca_system_score_gemma":0.000388831,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008431392,"about_ca_topic_score_gemma":0.00002479555,"domain_scores_codex":[0.9981863,0.00006691021,0.0003354228,0.0008185708,0.0001379301,0.0004548602],"domain_scores_gemma":[0.9983106,0.0003488817,0.0002498998,0.000644373,0.0002328237,0.0002134105],"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":[0.0001662506,0.0006048949,0.05083244,0.001119685,0.0002341473,0.001173659,0.003467883,0.7135252,0.0006086379,0.1812594,0.0007772063,0.04623051],"study_design_scores_gemma":[0.0003310799,0.00001779916,0.007728112,0.0006799114,0.00003695041,0.00003460679,0.0001070558,0.9092543,0.0001086529,0.0811573,0.0000324675,0.0005118212],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2659681,0.00006243552,0.7308134,0.00003058243,0.0006608062,0.0001313443,0.000004138578,0.0002648089,0.002064412],"genre_scores_gemma":[0.9701507,0.00005342999,0.0295582,0.00003193355,0.00006011537,0.000001055886,0.000007291434,0.00001386178,0.0001233755],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7041826,"threshold_uncertainty_score":0.9999014,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09727803126467462,"score_gpt":0.2333280409017815,"score_spread":0.1360500096371069,"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."}}