{"id":"W4407914197","doi":"10.1007/978-3-031-81596-6_8","title":"Memory Augmented Multi-agent Reinforcement Learning for Cooperative Environment","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Lethbridge","funders":"","keywords":"Computer science; Reinforcement learning; Human–computer interaction; Artificial intelligence","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":[0.001122334,0.0007846408,0.0007005855,0.0008775099,0.000644339,0.0005826943,0.00311614,0.0003440922,0.0000592925],"category_scores_gemma":[0.0002356171,0.0007556143,0.0002272679,0.0003846168,0.0005436214,0.0004924047,0.002302172,0.001109083,0.0000731837],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001154027,"about_ca_system_score_gemma":0.0006868585,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001165438,"about_ca_topic_score_gemma":0.000005483226,"domain_scores_codex":[0.9950135,0.00006317047,0.0009097791,0.001843709,0.00120956,0.0009602967],"domain_scores_gemma":[0.9968978,0.0006828245,0.0005218316,0.001428485,0.0002660185,0.0002030508],"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":[0.000008853331,0.00001932011,0.000007385393,0.00006207157,0.00003808419,0.00001657274,0.00061089,0.8789341,0.00009684241,0.004132101,0.00005510189,0.1160187],"study_design_scores_gemma":[0.0008666466,0.00046929,0.00001196939,0.0004513406,0.00002265251,0.000007237004,8.128894e-7,0.983972,0.002386098,0.0009486482,0.010126,0.0007373194],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000003280512,0.0002511076,0.9924333,0.0004674367,0.001726107,0.001638333,0.000002119599,0.00020622,0.003272105],"genre_scores_gemma":[0.0357178,0.0002590758,0.9117352,0.002622648,0.0003863077,0.0001746409,0.00007059032,0.00008637872,0.0489473],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1152814,"threshold_uncertainty_score":0.9994895,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02204631360071616,"score_gpt":0.2548871653478835,"score_spread":0.2328408517471673,"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."}}