搜索结果: 1-4 共查到“approximate dynamic programming”相关记录4条 . 查询时间(0.093 秒)
In this paper we describe an approximate dynamic programming policy for a discrete-time dynamical system perturbed by noise. The approximate value function is the pointwise supremum of a family of low...
Approximate Dynamic Programming via Iterated Bellman Inequalities
Convex Optimization Dynamic Programming Stochastic Control
2015/7/9
In this paper we introduce new methods for finding functions that lower bound the value function of a stochastic control problem, using an iterated form of the Bellman inequality. Our method is based ...
Quadratic Approximate Dynamic Programming for Input-Affine Systems
approximate dynamic programming stochastic control convex optimization
2015/7/9
We consider the use of quadratic approximate value functions for stochastic control problems with input-affine dynamics and convex stage cost and constraints. Evaluating the approximate dynamic progra...
Optimization-based Approximate Dynamic Programming
Approximate Dynamic Programming Approximate Linear Programming,
2014/12/18
Reinforcement learning algorithms hold promise in many complex domains, such as resource management and planning under uncertainty. Most reinforcement learning algorithms are iterative - they successi...