Delayed insertion and rule effect moderation of domain knowledge for reinforcement learning

Though not a fundamental pre-requisite to efficient machine learning, insertion of domain knowledge into adaptive virtual agent is nonetheless known to improve learning efficiency and reduce model complexity. Conventionally, domain knowledge is inserted prior to learning. Despite being effective, su...

Full description

Saved in:
Bibliographic Details
Main Authors: TENG, Teck-Hou, TAN, Ah-hwee
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2013
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/6651
https://ink.library.smu.edu.sg/context/sis_research/article/7654/viewcontent/Delayed_Insertion_and_Rule_Effect_Moderation_of_Domain_Knowledge___SSCI_2013.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
id sg-smu-ink.sis_research-7654
record_format dspace
spelling sg-smu-ink.sis_research-76542022-01-14T03:19:23Z Delayed insertion and rule effect moderation of domain knowledge for reinforcement learning TENG, Teck-Hou TAN, Ah-hwee Though not a fundamental pre-requisite to efficient machine learning, insertion of domain knowledge into adaptive virtual agent is nonetheless known to improve learning efficiency and reduce model complexity. Conventionally, domain knowledge is inserted prior to learning. Despite being effective, such approach may not always be feasible. Firstly, the effect of domain knowledge is assumed and can be inaccurate. Also, domain knowledge may not be available prior to learning. In addition, the insertion of domain knowledge can frame learning and hamper the discovery of more effective knowledge. Therefore, this work advances the use of domain knowledge by proposing to delay the insertion and moderate the effect of domain knowledge to reduce the framing effect while still benefiting from the use of domain knowledge. Using a non-trivial pursuit-evasion problem domain, experiments are first conducted to illustrate the impact of domain knowledge with different degrees of truth. The next set of experiments illustrates how delayed insertion of such domain knowledge can impact learning. The final set of experiments is conducted to illustrate how delaying the insertion and moderating the assumed effect of domain knowledge can ensure the robustness and versatility of reinforcement learning. 2013-04-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/6651 info:doi/10.1109/ADPRL.2013.6614999 https://ink.library.smu.edu.sg/context/sis_research/article/7654/viewcontent/Delayed_Insertion_and_Rule_Effect_Moderation_of_Domain_Knowledge___SSCI_2013.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Artificial Intelligence and Robotics Numerical Analysis and Scientific Computing
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Artificial Intelligence and Robotics
Numerical Analysis and Scientific Computing
spellingShingle Artificial Intelligence and Robotics
Numerical Analysis and Scientific Computing
TENG, Teck-Hou
TAN, Ah-hwee
Delayed insertion and rule effect moderation of domain knowledge for reinforcement learning
description Though not a fundamental pre-requisite to efficient machine learning, insertion of domain knowledge into adaptive virtual agent is nonetheless known to improve learning efficiency and reduce model complexity. Conventionally, domain knowledge is inserted prior to learning. Despite being effective, such approach may not always be feasible. Firstly, the effect of domain knowledge is assumed and can be inaccurate. Also, domain knowledge may not be available prior to learning. In addition, the insertion of domain knowledge can frame learning and hamper the discovery of more effective knowledge. Therefore, this work advances the use of domain knowledge by proposing to delay the insertion and moderate the effect of domain knowledge to reduce the framing effect while still benefiting from the use of domain knowledge. Using a non-trivial pursuit-evasion problem domain, experiments are first conducted to illustrate the impact of domain knowledge with different degrees of truth. The next set of experiments illustrates how delayed insertion of such domain knowledge can impact learning. The final set of experiments is conducted to illustrate how delaying the insertion and moderating the assumed effect of domain knowledge can ensure the robustness and versatility of reinforcement learning.
format text
author TENG, Teck-Hou
TAN, Ah-hwee
author_facet TENG, Teck-Hou
TAN, Ah-hwee
author_sort TENG, Teck-Hou
title Delayed insertion and rule effect moderation of domain knowledge for reinforcement learning
title_short Delayed insertion and rule effect moderation of domain knowledge for reinforcement learning
title_full Delayed insertion and rule effect moderation of domain knowledge for reinforcement learning
title_fullStr Delayed insertion and rule effect moderation of domain knowledge for reinforcement learning
title_full_unstemmed Delayed insertion and rule effect moderation of domain knowledge for reinforcement learning
title_sort delayed insertion and rule effect moderation of domain knowledge for reinforcement learning
publisher Institutional Knowledge at Singapore Management University
publishDate 2013
url https://ink.library.smu.edu.sg/sis_research/6651
https://ink.library.smu.edu.sg/context/sis_research/article/7654/viewcontent/Delayed_Insertion_and_Rule_Effect_Moderation_of_Domain_Knowledge___SSCI_2013.pdf
_version_ 1770576017209950208