{"id":"W3037941652","doi":"10.65109/hmve9255","title":"Gifting in Multi-Agent Reinforcement Learning","year":2020,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Reinforcement learning; Computer science; Function (biology); Reinforcement; Appropriation; Space (punctuation); Resource (disambiguation); Action (physics); Mechanism (biology); Property (philosophy); Error-driven learning; Artificial intelligence; Psychology; Social psychology","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":[],"consensus_categories":[],"category_scores_codex":[0.0002745281,0.0001309769,0.0001485288,0.00007560645,0.00008263332,0.0001422529,0.0006572633,0.00004106246,0.00009314403],"category_scores_gemma":[0.0002635034,0.0001259073,0.00004512964,0.0004533138,0.0000149956,0.0003645072,0.0004969765,0.0003199722,0.0004029831],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000619057,"about_ca_system_score_gemma":0.00003766949,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002893851,"about_ca_topic_score_gemma":0.000002026809,"domain_scores_codex":[0.9985965,0.00005770616,0.0003538336,0.0003226886,0.0003226875,0.0003465838],"domain_scores_gemma":[0.9994483,0.00005715766,0.00009902498,0.0002287589,0.00003430765,0.0001324349],"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":[0.000001525373,0.000005607278,0.005717473,0.00001147535,0.000004729784,0.0000149997,0.001889626,0.9845691,0.0003315076,0.005502688,0.0001025679,0.001848694],"study_design_scores_gemma":[0.0004521215,0.00009998434,0.001020702,0.00001448922,0.000001169525,0.000001159939,0.0001368441,0.9906121,0.0006179832,0.000004394727,0.006882393,0.0001566644],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001271139,0.00001543941,0.9845991,0.001647601,0.0001049373,0.0001502844,1.214957e-8,0.000313394,0.0118981],"genre_scores_gemma":[0.9030835,0.000009807051,0.09315719,0.00175293,0.00002752518,0.000006552085,0.000001565798,0.000009584084,0.001951346],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9018124,"threshold_uncertainty_score":0.5179666,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06128900177664424,"score_gpt":0.2753900464484899,"score_spread":0.2141010446718456,"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."}}