{"id":"W85998123","doi":"10.1609/icaps.v19i1.13355","title":"Incremental Policy Generation for Finite-Horizon DEC-POMDPs","year":2009,"lang":"en","type":"article","venue":"Proceedings of the International Conference on Automated Planning and Scheduling","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":64,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"National Science Foundation","keywords":"Dynamic programming; Computer science; Scalability; Reachability; Mathematical optimization; State (computer science); State space; Reduction (mathematics); Backup; Horizon; Algorithm; Mathematics","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":[0.001501223,0.0005849361,0.0008204827,0.0004420885,0.0004702579,0.000709361,0.001140796,0.0006472977,0.001852462],"category_scores_gemma":[0.004777886,0.0004604514,0.0004659542,0.000431663,0.0006782376,0.001199033,0.001105208,0.001330138,0.0002406454],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008007422,"about_ca_system_score_gemma":0.001297042,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002783373,"about_ca_topic_score_gemma":0.003537816,"domain_scores_codex":[0.9995235,0.0001668468,0.00002896228,0.0000823141,0.0001228299,0.00007557579],"domain_scores_gemma":[0.9972832,0.002049479,0.0001551637,0.0002269709,0.0001888317,0.00009638236],"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":[0.0001193831,0.00005961927,0.0005233021,0.00008821355,0.00002091102,0.00008614371,0.00004902323,0.9473028,0.0009667077,0.01009326,0.000782795,0.0399078],"study_design_scores_gemma":[0.0000108454,0.00001511673,0.00003513092,0.000004241344,0.000002989667,0.00001182219,0.000008866974,0.9933541,0.0005545018,0.005666673,0.0003329701,0.000002695453],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03969911,0.0002739655,0.9554786,0.0002191388,0.00005236039,0.00009008132,0.0001383048,0.001278843,0.002769599],"genre_scores_gemma":[0.7471653,0.0002056062,0.2509288,0.0001131279,0.00001757582,0.0002188153,0.0003088528,0.0001142705,0.0009276991],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002783373,"threshold_uncertainty_score":0.007939279,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05613533112334739,"score_gpt":0.3179825863431371,"score_spread":0.2618472552197897,"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."}}