{"id":"W1979239334","doi":"10.1109/acc.2010.5530771","title":"An investigation of guarding a territory problem in a grid world","year":2010,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Reinforcement learning; Computer science; Minimax; Grid; Artificial intelligence; Climbing; Hill climbing; Machine learning; Mathematical optimization; Geography; 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":[0.000410782,0.000478578,0.0008164871,0.0002975973,0.0008314347,0.0008651047,0.001083894,0.001147375,0.002537805],"category_scores_gemma":[0.001636727,0.0002695462,0.0005944524,0.0004495498,0.001240143,0.002197482,0.00128067,0.00104654,0.0001928151],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006577069,"about_ca_system_score_gemma":0.0007140267,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005486682,"about_ca_topic_score_gemma":0.003330489,"domain_scores_codex":[0.9996456,0.0001499512,0.00001327936,0.00006638371,0.00005972418,0.00006509582],"domain_scores_gemma":[0.9992201,0.0004579998,0.0001114993,0.00004617507,0.00006280959,0.0001013578],"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":[0.00009792346,0.00006436656,0.00227103,0.0001888374,0.00006324651,0.0008588509,0.0001765875,0.8389902,0.002507691,0.1376902,0.001457519,0.0156336],"study_design_scores_gemma":[0.00001866783,0.00006577829,0.000323227,0.00001001121,0.00001492575,0.0001540854,0.0001041246,0.9698948,0.0003174145,0.02756368,0.001522957,0.00001017004],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1307977,0.0009310176,0.8501005,0.0008677054,0.0001024355,0.0001030091,0.00008868743,0.0001369961,0.01687192],"genre_scores_gemma":[0.9284443,0.0007538447,0.06602409,0.0000904375,0.00004158029,0.0000904808,0.00006906089,0.00003346395,0.004452664],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005486682,"threshold_uncertainty_score":0.01090944,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01164173669835898,"score_gpt":0.2461753369648395,"score_spread":0.2345336002664805,"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."}}