Leveraging Domain Knowledge for Reinforcement Learning Using MMC Architectures

机译：利用领域知识进行MMC架构的强化学习

获取原文

页面导航

摘要
著录项
相似文献
相关主题

摘要

Despite the success of reinforcement learning methods in various simulated robotic applications, end-to-end training suffers from extensive training times due to high sample complexity and does not scale well to realistic systems. In this work, we speed up reinforcement learning by incorporating domain knowledge into policy learning. We revisit an architecture based on the mean of multiple computations (MMC) principle known from computational biology and adapt it to solve a "reacher task". We approximate the policy using a simple MMC network, experimentally compare this idea to end-to-end deep learning architectures, and show that our approach reduces the number of interactions required to approximate a suitable policy by a factor of ten.

机译：尽管强化学习方法在各种模拟机器人应用中都取得了成功，但是由于高样本复杂性，端到端训练仍然要花费大量的训练时间，并且无法很好地适应实际系统。在这项工作中，我们通过将领域知识整合到策略学习中来加快强化学习。我们基于计算生物学中已知的多次计算（MMC）原理重新审视体系结构，并使其适应于解决“扩展任务”。我们使用一个简单的MMC网络对策略进行近似，通过实验将该思想与端到端深度学习架构进行比较，并表明我们的方法将近似于合适策略所需的交互次数减少了十分之一。

著录项

来源
《International Conference on Artificial Neural Networks》|2019年|595-607|共13页
会议地点
作者
Rajkumar Ramamurthy; Christian Bauckhage; Rafet Sifa; Jannis Schuecker; Stefan Wrobel;
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
关键词

相似文献

外文文献
中文文献
专利

1. A priori-knowledge/actor-critic reinforcement learning architecture for computing the mean-variance customer portfolio: The case of bank marketing campaigns [J] . Emma M. Sanchez, Julio B. Clempner, Alexander S. Poznyak Engineering Applications of Artificial Intelligence . 2015,第NOVaPTaA期

机译：用于计算均值方差客户组合的先验知识/行为者批评强化学习架构：银行营销活动的案例
2. Robotic Information Gathering With Reinforcement Learning Assisted by Domain Knowledge: An Application to Gas Source Localization [J] . Thomas Wiedemann, Cosmin Vlaicu, Josip Josifovski, Quality Control, Transactions . 2021,第1期

机译：通过域知识协助的钢筋学习聚集的机器人信息：气源定位的应用
3. Incorporating domain knowledge into reinforcement learning to expedite welding sequence optimization [J] . Jesus Romero-Hdz, Baidya Nath Saha, Seiichiro Tstutsumi, Engineering Applications of Artificial Intelligence . 2020,第May期

机译：将领域知识整合到强化学习中以加快焊接顺序优化
4. Leveraging Domain Knowledge for Reinforcement Learning Using MMC Architectures [C] . Rajkumar Ramamurthy, Christian Bauckhage, Rafet Sifa, International Conference on Artificial Neural Networks . 2019

机译：利用MMC架构利用域名知识进行强化学习
5. Transfer in Deep Reinforcement Learning: How an Agent Can Leverage Knowledge from Another Agent, a Human, or Itself [D] . Du, Yunshu. 2021

机译：在深度加强学习中转移：代理人如何利用来自其他代理人，人类或本身的知识
6. Real-Time Task Assignment Approach Leveraging Reinforcement Learning with Evolution Strategies for Long-Term Latency Minimization in Fog Computing [O] . Long Mai, Nhu-Ngoc Dao, Minho Park 2018

机译：实时任务分配方法利用强化学习和演化策略使雾计算中的长期延迟最小化
7. Leveraging human knowledge in tabular reinforcement learning: a study of human subjects [O] . Ariel Rosenfeld, Moshe Cohen, Matthew E. Taylor, 2018

机译：利用表格钢筋学习的人类知识：对人类受试者的研究
8. KI-LEARN: Knowledge-Intensive Learning Methods for Knowledge-Rich/Data- Poor Domains [R] . Dietterich, T. G. , Restificar, A. , Tadepalli, P. , 2006

机译：KI-LEaRN：知识丰富/数据贫乏领域的知识密集型学习方法

Leveraging Domain Knowledge for Reinforcement Learning Using MMC Architectures

摘要

著录项

相似文献

相关主题

期刊订阅