{"id":"W2552186722","doi":"10.1109/fuzz-ieee.2016.7737798","title":"Reinforcement learning in the guarding a territory game","year":2016,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Guard (computer science); Reinforcement learning; Computer science; Game theory; A priori and a posteriori; Set (abstract data type); Artificial intelligence; Repeated game; Non-cooperative game; Mathematical economics; 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":[0.0007806756,0.0001101666,0.00009764003,0.000111964,0.00008094787,0.0001447377,0.001077626,0.00003788209,0.00006462984],"category_scores_gemma":[0.0001267396,0.00005543324,0.00004942441,0.0002055684,0.00003540604,0.0004862408,0.0002512932,0.0001687907,0.0002165383],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008417336,"about_ca_system_score_gemma":0.00003788032,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002494303,"about_ca_topic_score_gemma":0.000003275922,"domain_scores_codex":[0.9986558,0.0001216388,0.0002549155,0.0002251015,0.00040692,0.0003356474],"domain_scores_gemma":[0.9990998,0.0002707565,0.00007810308,0.0004939244,0.00002271191,0.00003469555],"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":[0.000005293087,0.00001657496,0.0099857,0.00001156358,0.00001712326,0.00003574235,0.003669486,0.805122,0.001900568,0.1390028,0.002674214,0.03755898],"study_design_scores_gemma":[0.001389811,0.0003818735,0.009376571,0.0001912872,0.0000059993,0.00003708391,0.0004754155,0.7894061,0.001217916,0.0008289701,0.1961614,0.0005276102],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001719299,0.00001070921,0.9497309,0.002905963,0.0001856028,0.0001314156,1.303019e-8,0.0001585846,0.04515754],"genre_scores_gemma":[0.9854962,0.00001424003,0.003461553,0.0007330331,0.00006393428,0.00001697676,2.738152e-7,0.000006120226,0.0102077],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9837769,"threshold_uncertainty_score":0.2783234,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01692262368708923,"score_gpt":0.2410897727366685,"score_spread":0.2241671490495792,"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."}}