{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002506356,0.0009800727,0.0009946381,0.0007977057,0.0003486485,0.001080773,0.001072117,0.0007954275,0.003055534],"category_scores_gemma":[0.01053251,0.0005258677,0.0006908305,0.0006733961,0.001990936,0.001840737,0.001222634,0.001843532,0.0004105825],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002432743,"about_ca_system_score_gemma":0.001847877,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004300633,"about_ca_topic_score_gemma":0.003653439,"domain_scores_codex":[0.9989105,0.0005904651,0.00004043313,0.0001748572,0.0002086881,0.00007485589],"domain_scores_gemma":[0.9955915,0.003627609,0.0002187874,0.0002277478,0.0001725089,0.000161866],"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":[0.0000649627,0.00003754049,0.0005019957,0.00007430699,0.00002580085,0.00002903495,0.00005311089,0.930358,0.0004249724,0.0507293,0.0005909545,0.01711006],"study_design_scores_gemma":[0.000008307155,0.00002165251,0.00006790135,0.000009488715,0.00000411635,0.000006466634,0.000004039212,0.9636475,0.0002039205,0.03572674,0.0002957043,0.000004032823],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01864048,0.0004363778,0.9773759,0.0003701771,0.00002583492,0.00005305615,0.0001063764,0.0004290863,0.002562713],"genre_scores_gemma":[0.7648377,0.0006338664,0.2292462,0.0001877285,0.00005886782,0.0003641905,0.0003135804,0.000279749,0.004078023],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004300633,"threshold_uncertainty_score":0.0176509,"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."}}