{"id":"W3006301096","doi":"10.48550/arxiv.2002.05147","title":"Multi-Agent Reinforcement Learning and Human Social Factors in Climate Change Mitigation","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Environmental Education and Sustainability","field":"Environmental Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Marl; Climate change; Social dilemma; Social learning; Reinforcement learning; Dilemma; Global warming; Software deployment; Computer science; Environmental planning; Risk analysis (engineering); Knowledge management; Business; Artificial intelligence; Psychology; Ecology; Social psychology; Environmental science","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":[0.003063931,0.0004345829,0.0004971938,0.0003117658,0.0004871099,0.0009209829,0.0007736124,0.001146899,0.001473608],"category_scores_gemma":[0.01359645,0.000212876,0.0003324464,0.0002510204,0.001994294,0.001418883,0.00129317,0.001479173,0.0001445256],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001198735,"about_ca_system_score_gemma":0.001374753,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004566127,"about_ca_topic_score_gemma":0.003938362,"domain_scores_codex":[0.9984468,0.001151275,0.00003282851,0.0001331143,0.0001392976,0.00009675061],"domain_scores_gemma":[0.9917365,0.00658353,0.0006733062,0.000263492,0.0003581865,0.0003849466],"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":[0.00007267985,0.0001456481,0.003264352,0.00009877636,0.00007767825,0.0001316923,0.0002719643,0.8671011,0.0009399037,0.09706362,0.001353578,0.02947898],"study_design_scores_gemma":[0.00002107631,0.00003246884,0.0002748297,0.00001322468,0.000006682812,0.00001287512,0.00004196469,0.9419987,0.0002668687,0.05590703,0.001415428,0.000008847666],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1064122,0.0009839404,0.8661403,0.006948036,0.0002086949,0.0001094049,0.0000418979,0.0003769477,0.01877849],"genre_scores_gemma":[0.9370556,0.0002750217,0.05984753,0.0003806483,0.00006857886,0.00009521768,0.00001857451,0.00002900305,0.002229753],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004566127,"threshold_uncertainty_score":0.01620382,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08009972006138026,"score_gpt":0.2302446621826246,"score_spread":0.1501449421212444,"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."}}