{"id":"W2128862550","doi":"10.65109/mphg3605","title":"Multi-Agent Patrolling with Reinforcement Learning","year":2004,"lang":"en","type":"preprint","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":107,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Patrolling; Reinforcement learning; Computer science; Task (project management); Adaptation (eye); Domain (mathematical analysis); Variety (cybernetics); Artificial intelligence; Distributed computing; Machine learning; Engineering","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004784334,0.0005835918,0.0004923408,0.0002649472,0.0002737943,0.0007574204,0.001965123,0.0002836189,0.00007821796],"category_scores_gemma":[0.00005989656,0.0004771577,0.0001889055,0.0002567201,0.00006192465,0.0002997553,0.002946445,0.001711033,0.0002464719],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005053272,"about_ca_system_score_gemma":0.0005529025,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001739347,"about_ca_topic_score_gemma":0.000007924238,"domain_scores_codex":[0.996508,0.00008747569,0.0006598637,0.00102877,0.001002563,0.0007133133],"domain_scores_gemma":[0.9974886,0.00006331885,0.0005702273,0.001448595,0.0002152358,0.000214056],"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":[0.000006799171,0.00002231977,0.0005284863,0.0001158143,0.0001089309,0.00004320408,0.0007574465,0.9946941,0.00002842874,0.003000938,0.00002704631,0.0006664811],"study_design_scores_gemma":[0.0009510854,0.0002643519,0.0002082647,0.0003891645,0.0000321125,0.00001115596,0.00005260465,0.9952416,0.000327281,0.00008203669,0.00176738,0.0006728944],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.000475413,0.00008169117,0.9896591,0.0002790062,0.0006863449,0.0006863187,1.886088e-7,0.0009766743,0.00715527],"genre_scores_gemma":[0.5661249,0.00008076506,0.4253255,0.0002522182,0.00008807553,0.00006309093,0.00002806255,0.00004496697,0.007992481],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5656495,"threshold_uncertainty_score":0.999768,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02931257123041275,"score_gpt":0.2582969557574918,"score_spread":0.228984384527079,"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."}}