{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003083217,0.0001268496,0.0001172397,0.0001721926,0.0001778917,0.0003484275,0.0007217148,0.00006238276,0.000002157872],"category_scores_gemma":[0.0003896973,0.0001030129,0.00004422824,0.000156654,0.0000217889,0.0003375137,0.0001105284,0.0001224905,0.000001359284],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006150985,"about_ca_system_score_gemma":0.00007066078,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004935337,"about_ca_topic_score_gemma":1.059468e-7,"domain_scores_codex":[0.9989807,0.000005441349,0.000262304,0.0002377186,0.0003473409,0.0001664918],"domain_scores_gemma":[0.9992455,0.00006039364,0.0002614639,0.00008025338,0.0003101354,0.00004227408],"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":[0.00004902769,0.00005552316,0.002078203,0.00003164033,0.00007153163,5.842673e-7,0.001293653,0.1327904,0.1811033,0.6777719,0.0005655419,0.004188742],"study_design_scores_gemma":[0.0003021205,0.0002347583,0.0006775631,0.0001725074,0.000006044,0.000005400974,0.00008238517,0.9712363,0.02542849,0.001668094,0.00007779745,0.0001085434],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8231798,0.0000313772,0.1569118,0.007752398,0.0005918416,0.0003952573,0.000005485992,0.0007152855,0.01041676],"genre_scores_gemma":[0.9512043,0.000008926823,0.04823408,0.0003300742,0.0001293299,0.000007084646,0.00000504657,0.000005372223,0.00007577545],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8384459,"threshold_uncertainty_score":0.4200745,"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."}}