{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002267978,0.0007948197,0.0009746797,0.0003194136,0.0004343079,0.0006228805,0.001250694,0.001101215,0.001926685],"category_scores_gemma":[0.008298204,0.0002882154,0.0003706283,0.0001989768,0.001940819,0.001319465,0.0009349764,0.001418497,0.0001741824],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001119606,"about_ca_system_score_gemma":0.001246586,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006681316,"about_ca_topic_score_gemma":0.004022793,"domain_scores_codex":[0.9989088,0.0006252498,0.00003081117,0.000148705,0.0001399303,0.0001465556],"domain_scores_gemma":[0.9943551,0.004491213,0.000401103,0.0001191002,0.0002913183,0.0003421413],"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":[0.0002259524,0.0001434398,0.00117721,0.00005328042,0.0000331499,0.0001185316,0.00010152,0.9697356,0.0009144111,0.01516637,0.0003001101,0.01203042],"study_design_scores_gemma":[0.00002970616,0.00007069938,0.0001104812,0.000004017777,0.000004304764,0.00001122322,0.0000135668,0.9942091,0.0002142026,0.005201763,0.0001260428,0.000005041392],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3041514,0.0003190535,0.6860883,0.0007247552,0.00005810695,0.0001592652,0.00003965835,0.0002889743,0.008170476],"genre_scores_gemma":[0.9719283,0.00007515967,0.02612884,0.00009338726,0.00001777916,0.00008014237,0.00001776127,0.00001636306,0.001642225],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006681316,"threshold_uncertainty_score":0.01328486,"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."}}