{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003038504,0.0006178961,0.0009924202,0.000439587,0.0006625648,0.0009753843,0.001123026,0.001274153,0.001820195],"category_scores_gemma":[0.01404614,0.0002912773,0.0004830302,0.0004153796,0.002584662,0.001987122,0.00141185,0.0015205,0.0001793415],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001424373,"about_ca_system_score_gemma":0.0007409257,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001555453,"about_ca_topic_score_gemma":0.0009501568,"domain_scores_codex":[0.9986694,0.0007872953,0.00005599435,0.0001778515,0.0002044237,0.000105132],"domain_scores_gemma":[0.993691,0.004264402,0.0007545998,0.0004389365,0.0003959386,0.0004552914],"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":[0.0001304244,0.00007546785,0.0020024,0.0001472009,0.00007094121,0.0001850209,0.0002029429,0.5913201,0.001628518,0.3777799,0.000669421,0.02578773],"study_design_scores_gemma":[0.00004426126,0.00007333881,0.000253366,0.00001622312,0.00001226032,0.00003560925,0.00002124912,0.8094869,0.0003681331,0.1886483,0.001026552,0.00001384499],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1041104,0.001122207,0.8839084,0.001129131,0.0001112025,0.00006908488,0.00004597487,0.0002882291,0.009215483],"genre_scores_gemma":[0.9631036,0.0003318829,0.03446406,0.00009224232,0.00004192603,0.00006997804,0.00001677435,0.00002246284,0.001857184],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003038504,"threshold_uncertainty_score":0.01606935,"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."}}