Action-Based State Space Construction for Robot Learning
Action-Based State Space Construction for Robot Learning
复制标题
基于动作的机器人学习状态空间构建
DOI:
10.7210/jrsj.15.886
复制
发表时间:
1997
期刊:
影响因子:
--
通讯作者:
K. Hosoda
中科院分区:
文献类型:
--
作者:
M. Asada;S. Noda;K. Hosoda
Robot learning such as reinforcement learning generally needs a well-defined state space in order to converge. However, to build such a state space is one of the main issues of the robot learning because of the inter-dependence between state and action spaces, which resembles to the well known“chicken and egg”problem. This paper proposes a method of action-based state space construction for vision-based mobile robots. Basic ideas to cope with the interdependence are that we define a state as a cluster of input vectors from which the robot can reach the goal state or the state already obtained by a sequence of one kind action primitive regardless of its length, and that this sequence is defined as one action. To realize these ideas, we need many data (experiences) of the robot and cluster the input vectors as hyper ellipsoids so that the whole state space is segmented into a state transition map in terms of action from which the optimal action sequence is obtained. To show the validity of the method, we apply it to a soccer robot which tries to shoot a ball into a goal. The simulation and real experiments are shown.
DOI:
--
发表时间:
2009
期刊:
影响因子:
--
作者:
Takemi Mori;Masaru Takahashi;Ken-ichi Kanto & Ken-ichi Ohbuchi;Masaru Takahashi & Takemi Mori;森丈弓;森丈弓;森 丈弓・高橋 哲・菅藤健一・丸山もゆる・相澤 優・石黒裕子・内山八重・小野広明・吉澤 淳・大渕憲一;森丈弓;森 丈弓・菅藤健一・高橋 哲・丸山もゆる・相澤 優・石黒裕子・内山八重・小野広明・吉澤 淳・大渕憲一
通讯作者:
森 丈弓・菅藤健一・高橋 哲・丸山もゆる・相澤 優・石黒裕子・内山八重・小野広明・吉澤 淳・大渕憲一