Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/83043
Title: Knowledge Transfer for Deep Reinforcement Learning with Hierarchical Experience Replay
Authors: Yin, Haiyan
Pan, Sinno Jialin
Keywords: Deep reinforcement learning
Policy distillation
Issue Date: 2017
Source: Yin, H., & Pan, S. J. (2017). Knowledge Transfer for Deep Reinforcement Learning with Hierarchical Experience Replay. Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence (AAAI-17), 1640-1646.
Conference: Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence (AAAI-17)
Abstract: The process for transferring knowledge of multiple reinforcement learning policies into a single multi-task policy via distillation technique is known as policy distillation. When policy distillation is under a deep reinforcement learning setting, due to the giant parameter size and the huge state space for each task domain, it requires extensive computational efforts to train the multi-task policy network. In this paper, we propose a new policy distillation architecture for deep reinforcement learning, where we assume that each task uses its task specific high-level convolutional features as the inputs to the multi-task policy network. Furthermore, we propose a new sampling framework termed hierarchical prioritized experience replay to selectively choose experiences from the replay memories of each task domain to perform learning on the network. With the above two attempts, we aim to accelerate the learning of the multi-task policy network while guaranteeing a good performance. We use Atari 2600 games as testing environment to demonstrate the efficiency and effectiveness of our proposed solution for policy distillation.
URI: https://hdl.handle.net/10356/83043
http://hdl.handle.net/10220/42453
URL: https://aaai.org/ocs/index.php/AAAI/AAAI17/paper/view/14478
Schools: School of Computer Science and Engineering 
Rights: © 2017 Association for the Advancement of Artificial Intelligence. This is the author created version of a work that has been peer reviewed and accepted for publication by Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence (AAAI-17), Association for the Advancement of Artificial Intelligence. It incorporates referee’s comments but changes resulting from the publishing process, such as copyediting, structural formatting, may not be reflected in this document. The published version is available at: [https://aaai.org/ocs/index.php/AAAI/AAAI17/paper/view/14478].
Fulltext Permission: open
Fulltext Availability: With Fulltext
Appears in Collections:SCSE Conference Papers

Files in This Item:
File Description SizeFormat 
Knowledge Transfer for Deep Reinforcement Learning with Hierarchical Experience Replay.pdf5.3 MBAdobe PDFThumbnail
View/Open

Page view(s) 50

602
Updated on Jun 13, 2024

Download(s) 50

153
Updated on Jun 13, 2024

Google ScholarTM

Check

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.