{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009295625,0.0006098769,0.0006488987,0.0006783214,0.000426765,0.0009724643,0.001226867,0.0008524017,0.006979271],"category_scores_gemma":[0.003070351,0.0003091906,0.0005946842,0.0005233989,0.0005907865,0.001427126,0.001033462,0.001477825,0.001391708],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001055426,"about_ca_system_score_gemma":0.001551472,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00588685,"about_ca_topic_score_gemma":0.00775491,"domain_scores_codex":[0.9996386,0.0001260979,0.00002832627,0.00007360692,0.00009893697,0.00003445978],"domain_scores_gemma":[0.9992815,0.0003043014,0.00005436222,0.0001270949,0.0001659453,0.00006689933],"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":[0.0006421441,0.0002184821,0.001042742,0.0003306505,0.00008813383,0.0001942069,0.0001241585,0.5040024,0.004956281,0.1910735,0.02917764,0.2681497],"study_design_scores_gemma":[0.00003111059,0.00002876239,0.00009588798,0.00001590053,0.00001373682,0.00003266247,0.00001025572,0.8995678,0.001653776,0.08935808,0.00918216,0.000009831511],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003725223,0.0001239891,0.9866676,0.000193353,0.000142009,0.00008172087,0.0007976446,0.005330429,0.002937856],"genre_scores_gemma":[0.3684182,0.0004136431,0.6181701,0.0003491809,0.00008897608,0.0006619643,0.002634406,0.0008938048,0.008369761],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006979271,"threshold_uncertainty_score":0.02334791,"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."}}