{"id":"W3035431356","doi":"10.48550/arxiv.2006.06054","title":"Marginal Utility for Planning in Continuous or Large Discrete Action Spaces","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Alberta Machine Intelligence Institute; Compute Canada","keywords":"Generator (circuit theory); Action (physics); Computer science; Domain (mathematical analysis); Sample (material); Space (punctuation); Artificial intelligence; State space; Marginal utility; Machine learning; Mathematics; Statistics; Economics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0003500777,0.0002773762,0.0003866139,0.0001932896,0.0001372073,0.0001866625,0.001408607,0.0002470603,0.00003469954],"category_scores_gemma":[0.0001370473,0.000293097,0.0001686013,0.0004661883,0.0000892183,0.0004866231,0.001335939,0.0005546016,0.00003459162],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001678104,"about_ca_system_score_gemma":0.0002032614,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001988791,"about_ca_topic_score_gemma":0.0003873766,"domain_scores_codex":[0.9979446,0.0001269917,0.0002523278,0.001136645,0.00009249203,0.00044694],"domain_scores_gemma":[0.9985991,0.0002624422,0.0002577105,0.0006493512,0.00009712339,0.0001342816],"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":[0.004018376,0.0007614489,0.211797,0.001395447,0.0004375595,0.00416277,0.01250112,0.2687421,0.0004255171,0.4674466,0.004177327,0.02413475],"study_design_scores_gemma":[0.0002548702,0.0001118007,0.002675219,0.0001469649,0.00002911462,0.00000263583,0.001114562,0.9401746,0.0007418547,0.04999431,0.004329791,0.0004242914],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2012656,0.00002857958,0.7963992,0.0003458974,0.0005951773,0.0004643716,0.00003269488,0.0001876416,0.000680847],"genre_scores_gemma":[0.9958323,0.00003033828,0.003332891,0.0000831967,0.0001041354,0.000003702797,0.00001451183,0.0000145973,0.0005843081],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7945668,"threshold_uncertainty_score":0.9999521,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2101081257367713,"score_gpt":0.2802973818557379,"score_spread":0.07018925611896662,"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."}}