摘要：The general relationship between RL and MDP is that RL is a framework for solving problems that can be expressed as MDPs. DP requires you to fully des 阅读全文

摘要：1. 《Variational Inference》:知道observation x, 求hidden variable z的posterior distribution p(z | x, \alpha). Main idea是用一个 q(z_{1:m} | v) 来近似这个posterior di 阅读全文

摘要：Estimating the use of higher order theory of mind using computational agents 1. a pedestrian who wants to cross a street behaves differently depending 阅读全文