A robot that reinforcement-learns to identify and memorize important previous observations
A robot that reinforcement-learns to identify and memorize important previous observations
复制标题
一种通过强化学习来识别和记忆之前的重要观察结果的机器人
DOI：
10.1109/iros.2003.1250667
复制
发表时间：
2003
期刊：
影响因子：
--
通讯作者：
J. Schmidhuber
中科院分区：
文献类型：
--
作者：
B. Bakker;Viktor Zhumatiy;G. Gruener;J. Schmidhuber
传统的强化学习算法很难应用于机器人，由于大的和连续的域，部分可观测性和有限数量的学习经验的问题。本文通过结合以下内容来解决这些问题：（1）强化学习与记忆，使用LSTM递归神经网络实现，其输入是从原始输入中提取的离散事件;（2）在线探索和离线策略学习。一个真实的机器人的实验证明了该方法的可行性。
It is difficult to apply traditional reinforcement learning algorithms to robots, due to problems with large and continuous domains, partial observability, and limited numbers of learning experiences. This paper deals with these problems by combining: (1) reinforcement learning with memory, implemented using an LSTM recurrent neural network whose inputs are discrete events extracted from raw inputs; (2) online exploration and offline policy learning. An experiment with a real robot demonstrates the methodology's feasibility.
影响因子：
1.3
作者：
Barruquer Moner
通讯作者：
Barruquer Moner