搜索资源列表
policy-gradient-algorithms
- 关于策略梯度policy gradient 的一篇重要的博士论文,是一个澳大利亚的博士学位论文,对于研究pomdp及其策略梯度解法的人应该有帮助吧-Gradient on the strategy of an important policy gradient doctoral dissertation, is an Australian PhD thesis, and its strategy for research pomdp gradient solution should be to
pomdp1
- 求解POMDP问题的一个重要方法,对策略空间进行简化-We propose a new approach to the problem of searching a space of policies for a Markov decision process (MDP) or a partially observable Markov decision process (POMDP), given a model.
10.1.1.61.2009
- 对pomdp的求解算法进行了详细分析,可以实现,对于想学习POMDP理论的人,是很好的材料-The solution algorithm for pomdp a detailed analysis can be achieved, for people who want to learn POMDP theory, is a good material
1107.0053v1
- 对POMDP信念空间进行压缩,加速求解流程,值得学习-POMDP belief space of the compression, acceleration solution process, it is worth learning
Decentralized
- 介绍关于认知无线电机会频谱接入中,基于POMDP的实现认知用户吞吐量最大的一种算法,主要是在自组网环境中。-Introduction of cognitive radio spectrum access opportunities, the POMDP-based implementation of a cognitive user maximum throughput algorithm, mainly in the ad hoc network environment.
Optimal Cost and Policy for a Markovian Replacement Problem
- Partially Observable Markov decision model for a replacement/inventory problem. Cost is solved in closed form.