{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003710774,0.00006167929,0.0000829874,0.0002217089,0.00002347456,0.00005845424,0.0004821473,0.00003185202,0.00001446761],"category_scores_gemma":[0.0000155812,0.00005720511,0.00001764321,0.0003286488,0.00003975501,0.0006074199,0.00008158903,0.0001917355,0.000008139082],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001538812,"about_ca_system_score_gemma":0.00005345781,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001111804,"about_ca_topic_score_gemma":0.000283672,"domain_scores_codex":[0.9992737,0.00003482768,0.0002196056,0.0001616392,0.0001770786,0.000133159],"domain_scores_gemma":[0.9994496,0.00003603716,0.00008336612,0.0003576934,0.00003292153,0.00004044447],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003298505,0.00003743178,0.3522438,0.00004185421,0.00000815463,0.000005250312,0.004491254,0.3306785,0.1354785,0.1714526,0.001146134,0.004413328],"study_design_scores_gemma":[0.0002579639,0.00008843032,0.04227102,0.00004048248,0.000001696578,0.000002869321,0.00004156296,0.9368616,0.01770002,0.001672583,0.0009047973,0.0001570275],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.419495,0.000002358935,0.5689026,0.0004402381,0.0007983478,0.0002148181,1.07727e-7,0.0001532264,0.009993323],"genre_scores_gemma":[0.7531316,2.749296e-7,0.246345,0.00008979716,0.0000666941,0.000005156363,0.00000118766,0.000003525856,0.0003568558],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6061831,"threshold_uncertainty_score":0.2332757,"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."}}