{"id":"W3093827687","doi":"10.22215/etd/2016-11612","title":"Multi-Robot Learning in the Guarding a Territory Game","year":2016,"lang":"en","type":"dissertation","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Guard (computer science); Reinforcement learning; Computer science; A priori and a posteriori; Robot; Artificial intelligence; Game theory; Human–computer interaction; Mathematical economics; Mathematics; Epistemology","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":[0.0006913375,0.0002768736,0.0002523985,0.0002774863,0.0001461341,0.0003452062,0.001892898,0.0002250982,0.00004438149],"category_scores_gemma":[0.0001942943,0.0001731903,0.000122526,0.000241471,0.00002121081,0.000374665,0.0001109804,0.0007933286,0.0002549378],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009784588,"about_ca_system_score_gemma":0.000121674,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007427563,"about_ca_topic_score_gemma":0.00007266763,"domain_scores_codex":[0.9979354,0.0002301226,0.0004074465,0.0004654807,0.0005493537,0.0004121808],"domain_scores_gemma":[0.9987161,0.0002893627,0.0002646994,0.0006298039,0.00006015979,0.00003987443],"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":[0.0000518822,0.0002118494,0.01045824,0.0006074892,0.0002333069,0.0003176123,0.07223138,0.7243055,0.01132,0.02046514,0.004564407,0.1552332],"study_design_scores_gemma":[0.001957539,0.0003126205,0.0546402,0.001671792,0.00004499264,0.0000324083,0.004551922,0.8818487,0.001039315,0.0002514047,0.05178801,0.001861087],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001310903,0.0001029822,0.9493154,0.0003188714,0.001431428,0.0003424822,1.56925e-7,0.0002842168,0.04689355],"genre_scores_gemma":[0.6837742,0.00011775,0.04812562,0.0005862686,0.0004373402,0.0001263488,0.00008892038,0.00008021327,0.2666633],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9011898,"threshold_uncertainty_score":0.7062494,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02150014991520405,"score_gpt":0.2836851225046714,"score_spread":0.2621849725894674,"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."}}