未登录Deep reinforcement learning can promote sustainable human behaviour in a common-pool resource problem深度强化学习能够促进公共池资源问题中的人类可持续行为。
Koster, Raphael; Pislar, Miruna; Tacchetti, Andrea; Balaguer, Jan; Liu, Leqi; Elie, Romuald; Hauser, Oliver P.; Tuyls, Karl; Botvinick, Matt; Summerfield, Christopher .png)
分享.png)
收藏TacticAI: an AI assistant for football tacticsWang, Zhe; Velickovic, Petar; Hennes, Daniel; Tomasev, Nenad; Prince, Laurel; Kaisers, Michael; Bachrach, Yoram; Elie, Romuald; Wenliang, Li Kevin; Piccinini, Federico; Spearman, William; Graham, Ian; Connor, Jerome; Yang, Yi; Recasens, Adria; Khan, Mina; Beauguerlange, Nathalie; Sprechmann, Pablo; Moreno, Pol; Heess, Nicolas; Bowling, Michael; Hassabis, Demis; Tuyls, Karl 分享 收藏 From motor control to team play in simulated humanoid footballLiu, Siqi; Lever, Guy; Wang, Zhe; Merel, Josh; Eslami, S. M. Ali; Hennes, Daniel; Czarnecki, Wojciech M.; Tassa, Yuval; Omidshafiei, Shayegan; Abdolmaleki, Abbas; Siegel, Noah Y.; Hasenclever, Leonard; Marris, Luke; Tunyasuvunakool, Saran; Song, H. Francis; Wulfmeier, Markus; Muller, Paul; Haarnoja, Tuomas; Tracey, Brendan; Tuyls, Karl; Graepel, Thore; Heess, Nicolas 分享 收藏 Multiagent off-screen behavior prediction in footballOmidshafiei, Shayegan; Hennes, Daniel; Garnelo, Marta; Wang, Zhe; Recasens, Adria; Tarassov, Eugene; Yang, Yi; Elie, Romuald; Connor, Jerome T.; Muller, Paul; Mackraz, Natalie; Cao, Kris; Moreno, Pol; Sprechmann, Pablo; Hassabis, Demis; Graham, Ian; Spearman, William; Heess, Nicolas; Tuyls, Karl 分享 收藏 分享 收藏 α-Rank: Multi-Agent Evaluation by EvolutionOmidshafiei, Shayegan; Papadimitriou, Christos; Piliouras, Georgios; Tuyls, Karl; Rowland, Mark; Lespiau, Jean-Baptiste; Czarnecki, Wojciech M.; Lanctot, Marc; Perolat, Julien; Munos, Remi 分享 收藏 分享 收藏 分享 收藏 分享 收藏 分享 收藏 分享 收藏 分享 收藏 分享 收藏 
.png){kind=icon}
.png){kind=icon}
.png){kind=icon}
.png){kind=icon}
