Solving a Complex Prisoner's Dilemma with Self-Modifying Policies
FROM ANIMALS TO ANIMATS SERIES（1998）
摘要
Self-modifying policies (SMPs) trained by the success-story algorithm (SSA) have been successfully applied to various difficult reinforcement learning tasks (Schmidhuber et al. 1997a, 1997b). Here we present new results on an application where two cooperating/competing animats have to solve a complex version of the prisoner's dilemma.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树，研究论文发展脉络
Chat Paper
正在生成论文摘要