{"id":"W4391654576","doi":"10.1007/s10462-023-10670-6","title":"Learning team-based navigation: a review of deep reinforcement learning techniques for multi-agent pathfinding","year":2024,"lang":"en","type":"review","venue":"Artificial Intelligence Review","topic":"Robotic Path Planning Algorithms","field":"Computer Science","cited_by":39,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia, Okanagan Campus; University of British Columbia; University of Victoria","funders":"","keywords":"Pathfinding; Reinforcement learning; Computer science; Artificial intelligence; Human–computer interaction; Shortest path problem","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":[0.004983658,0.000869264,0.003325945,0.0003672539,0.000270933,0.0001718357,0.001827009,0.000287747,0.00003759674],"category_scores_gemma":[0.001950865,0.0007077128,0.001599198,0.002027459,0.0001048863,0.0002546534,0.0004150397,0.001261452,0.0003730986],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003581713,"about_ca_system_score_gemma":0.0006171991,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001004646,"about_ca_topic_score_gemma":3.927687e-7,"domain_scores_codex":[0.9930317,0.0007638478,0.003489503,0.001237396,0.0007728909,0.0007047083],"domain_scores_gemma":[0.9955437,0.0006598028,0.002072654,0.001052663,0.0004803627,0.0001907716],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"systematic_review","study_design_scores_codex":[3.422674e-7,0.00002416544,7.080504e-8,0.3637782,0.00005274355,0.00001294443,0.00004737387,0.0002334702,3.258884e-7,0.00121667,0.0001001932,0.6345335],"study_design_scores_gemma":[0.000006132587,0.0001633113,3.425584e-9,0.4928032,0.0007896508,0.00002826011,0.000006380803,0.07923237,0.00004565199,0.00006630417,0.4264542,0.0004045364],"study_design_candidate":"systematic_review","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[1.158947e-9,0.5089546,0.4878573,0.00007303496,0.0003015164,0.002504087,0.000002456371,0.0002491488,0.00005788095],"genre_scores_gemma":[6.011368e-7,0.8221686,0.1756646,0.0002394492,0.0001449239,0.001413634,0.0001817538,0.00007606493,0.0001103819],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.634129,"threshold_uncertainty_score":0.9995374,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1632568166785285,"score_gpt":0.4231300236244041,"score_spread":0.2598732069458756,"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."}}