{"id":"W4388551180","doi":"10.1007/s10458-023-09628-3","title":"ASN: action semantics network for multiagent reinforcement learning","year":2023,"lang":"en","type":"article","venue":"Autonomous Agents and Multi-Agent Systems","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Semantics (computer science); Artificial intelligence; Action (physics); Action selection; Artificial neural network; Multi-agent system; Programming language; Perception","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":[0.001033784,0.0003562682,0.0003980105,0.0001989714,0.0007791067,0.0005297711,0.0005337138,0.0001558317,0.00000768313],"category_scores_gemma":[0.00008618327,0.0003407899,0.0001437544,0.0004119226,0.00003895762,0.0003902216,0.0004270154,0.0002350032,0.0002146709],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001909576,"about_ca_system_score_gemma":0.00006483382,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001284435,"about_ca_topic_score_gemma":0.000006025089,"domain_scores_codex":[0.9971378,0.0001312546,0.0007305323,0.0006728976,0.0004484908,0.0008790228],"domain_scores_gemma":[0.9984505,0.0001743862,0.0004454863,0.000565514,0.0001308376,0.0002333283],"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":[0.000005528162,0.00002294842,0.002244665,0.000197118,0.0001152087,0.00001463633,0.000990572,0.9843906,0.0001360415,0.002202862,0.006256566,0.003423227],"study_design_scores_gemma":[0.0009559125,0.0001681401,0.003061454,0.00009140838,0.00003061205,0.000009899033,0.0002424809,0.8512602,0.00005534204,0.000006109,0.143784,0.0003344143],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008090792,0.0001510313,0.9851484,0.0002303316,0.003703816,0.001636824,0.000002448216,0.0008248229,0.0002115696],"genre_scores_gemma":[0.9615466,0.0004706599,0.01246109,0.000195581,0.000403608,0.0003066923,0.0001148115,0.00006315859,0.02443781],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9726873,"threshold_uncertainty_score":0.9999044,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08029373040729547,"score_gpt":0.3143184978309977,"score_spread":0.2340247674237022,"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."}}