Correcting flawed expert knowledge through reinforcement learning
作者：
Highlights：
• Reinforcement learning used to correct erroneous knowledge in a tactical agent.
• Such experiential learning also creates missing knowledge for a tactical agent.
• Prototype was built and extensively tested to verify usefulness of method.
摘要
•Reinforcement learning used to correct erroneous knowledge in a tactical agent.•Such experiential learning also creates missing knowledge for a tactical agent.•Prototype was built and extensively tested to verify usefulness of method.
论文关键词：Knowledge acquisition,Context-based reasoning,Reinforcement learning,Theory revision
论文评审过程：Available online 15 April 2015, Version of Record 15 May 2015.
论文官网地址：https://doi.org/10.1016/j.eswa.2015.04.015
