Model-free adaptive dynamic programming for optimal control of discrete-time affine nonlinear system | |
Xia ZP(夏中谱); Dongbin Zhao | |
2014-08 | |
会议日期 | 2014-08 |
会议地点 | South Africa |
关键词 | Model-free Adaptive Dynamic Programming Reinforcement Learning Policy Iteration Multilayer Perceptron Neural Network. |
英文摘要 |
In this paper, a model-free and effective approach is proposed to solve infinite horizon optimal control problem for affine nonlinear systems based on adaptive dynamic programming technique. The developed approach, referred to as the actor-critic structure, employs two multilayer perceptron neural networks to approximate the state-action value function and the control policy, respectively. It uses data collected arbitrarily from any reasonable sampling distribution for policy iteration. In the policy evaluation phase, a novel objective function is defined for updating the critic network, and thus makes the critic network converge to the Bellman equation directly rather than iteratively. In the policy improvement phase, the action network is updated to minimize the outputs of the critic network. The two phases alternate until no more improvement of the control policy is observed, such that the optimal control policy is achieved. Two simulation examples are provided to show the effectiveness of the approach. |
会议录 | Proceedings of International Federation of Automatic Control 2014 |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/11460] |
专题 | 自动化研究所_复杂系统管理与控制国家重点实验室_智能化团队 |
通讯作者 | Dongbin Zhao |
作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Xia ZP,Dongbin Zhao. Model-free adaptive dynamic programming for optimal control of discrete-time affine nonlinear system[C]. 见:. South Africa. 2014-08. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论