首页> 外文会议>日本ロボット学会学術講演会 >Characteristic of temperature-based reinforcement learning in learning-parameters - characteristic of convergence of learning and construction of state-space -

【24h】

Characteristic of temperature-based reinforcement learning in learning-parameters - characteristic of convergence of learning and construction of state-space -

机译：基于温度的增强学习参数的特征 - 学习趋同特征及状态空间施工 -

获取原文

页面导航

摘要
著录项
相似文献
相关主题

摘要

During STL (S-Temperature based reinforcement Learning), the robot system can compose the coordination of state-action. After completing the learning, the robotic system transits seamlessly to the task-achieving process. When the robot system accidentally confronts with unknown state of sensory data, it restarts the learning. This paper clarifies the learning characteristic of convergence of learning and construction of state-space in learning parameters by computer simulation experiment.

机译：在STL（基于S温度的强化学习）期间，机器人系统可以构成状态动作的协调。完成学习后，机器人系统无缝运输到任务实现过程。当机器人系统意外地面对有未知的感官数据状态时，它重新启动学习。本文通过计算机仿真实验阐明了学习参数学习参数学习与建设的学习特征。

著录项

来源
《日本ロボット学会学術講演会》|2000年||共2页
会议地点
作者
Tsutomu Sawada; Atsushi Sugai; Sumiaki Ichikawa; Fumio Hara;
展开▼
作者单位

展开▼
会议组织
原文格式 PDF
正文语种
中图分类 TP241-53;
关键词
STL; Characteristic of learning; Learning parameter;

机译：STL;学习的特征;学习参数;

相似文献

外文文献
中文文献
专利

1. An incremental state-space construction based on the notion of contradiction for reinforcement learning [J] . Hisashi Handa, Akira Ninomiya, Tadashi Horiuchi, 計測自動制御学会論文集 . 2002,第5期

机译：基于矛盾概念的增量状态空间构造，用于强化学习
2. An incremental state-space construction based on the notion of contradiction for reinforcement learning [J] . Hisashi Handa, Akira Ninomiya, Tadashi Horiuchi, 計測自動制御学会論文集 . 2002,第5期

机译：基于加强学习矛盾矛盾的增量状态空间施工
3. Multiagent-Based Simulation of Temporal-Spatial Characteristics of Activity-Travel Patterns Using Interactive Reinforcement Learning [J] . Min Yang, Yingxiang Yang, Wei Wang, Mathematical Problems in Engineering . 2014,第pta2期

机译：基于交互式增强学习的基于Multiagent的活动-出行方式时空特征模拟
4. Characteristic of temperature-based reinforcement learning in learning-parameters - characteristic of convergence of learning and construction of state-space - [C] . Tsutomu Sawada, Atsushi Sugai, Sumiaki Ichikawa, 日本ロボット学会学術講演会 . 2000

机译：基于温度的增强学习参数的特征 - 学习趋同特征及状态空间施工 -
5. Youths' motivated attention and reinforcement matching characteristics as moderators of the effects of parenting on adolescent communication and externalizing behaviors: A social learning, matching law approach [D] . Goodnight, Jackson A. 2010

机译：青少年的动机激励和强化匹配特征作为父母对青少年沟通和外在行为影响的调节剂：一种社会学习，匹配法
6. Computational Characteristics of the Striatal Dopamine System Described by Reinforcement Learning With Fast Generalization [O] . Yoshihisa Fujita, Sho Yagishita, Haruo Kasai, 2020

机译：快速泛化钢筋学习描述的纹状体多巴胺系统的计算特征
7. Computational characteristics of the striatal dopamine system described by reinforcement learning with fast generalization [O] . Yoshihisa Fujita, Sho Yagishita, Haruo Kasai, 2019

机译：快速泛化钢筋学习描述的纹状体多巴胺系统的计算特征

Characteristic of temperature-based reinforcement learning in learning-parameters - characteristic of convergence of learning and construction of state-space -

摘要

著录项

相似文献

相关主题

期刊订阅