Dataset Groups Activity Stream SMIX(λ): Enhancing Centralized Value SMIX(λ) is a method for cooperative multi-agent reinforcement learning that uses an off-policy training approach to estimate a centralized value function. BibTex: @dataset{Xinghu_Yao_and_Chao_Wen_and_Yuhui_Wang_and_Xiaoyang_Tan_2025, abstract = {SMIX(λ) is a method for cooperative multi-agent reinforcement learning that uses an off-policy training approach to estimate a centralized value function.}, author = {Xinghu Yao and Chao Wen and Yuhui Wang and Xiaoyang Tan}, doi = {10.57702/jnggwmso}, institution = {No Organization}, keyword = {'Centralized Value Function', 'Cooperative Multi-Agent Reinforcement Learning', 'Off-Policy Training'}, month = {jan}, publisher = {TIB}, title = {SMIX(λ): Enhancing Centralized Value}, url = {https://service.tib.eu/ldmservice/dataset/smix-----enhancing-centralized-value}, year = {2025} }
