Transferring expectations in model-based reinforcement learning

We study how to automatically select and adapt multiple abstractions or representations of the world to support model-based reinforcement learning. We address the challenges of transfer learning in heterogeneous environments with varying tasks. We present an efficient, online framework that, through...

Full description

Saved in:

Bibliographic Details
Main Authors:	Nguyen, Trung Thanh, Silander, Tomi, Tze-Yun LEONG
Format:	text
Language:	English
Published:	Institutional Knowledge at Singapore Management University 2012
Subjects:	Benchmark domains Faster convergence General approach Heterogeneous environments Mapping strategy Model-based reinforcement learning Potential impacts Transfer learning Numerical Analysis and Scientific Computing
Online Access:	https://ink.library.smu.edu.sg/sis_research/3049
Tags:	Add Tag No Tags, Be the first to tag this record!
Institution:	Singapore Management University
Language:	English

id	sg-smu-ink.sis_research-4049
record_format	dspace
spelling	sg-smu-ink.sis_research-40492016-02-05T06:30:05Z Transferring expectations in model-based reinforcement learning Nguyen, Trung Thanh Silander, Tomi Tze-Yun LEONG, We study how to automatically select and adapt multiple abstractions or representations of the world to support model-based reinforcement learning. We address the challenges of transfer learning in heterogeneous environments with varying tasks. We present an efficient, online framework that, through a sequence of tasks, learns a set of relevant representations to be used in future tasks. Without predefined mapping strategies, we introduce a general approach to support transfer learning across different state spaces. We demonstrate the potential impact of our system through improved jumpstart and faster convergence to near optimum policy in two benchmark domains. 2012-12-08T08:00:00Z text https://ink.library.smu.edu.sg/sis_research/3049 Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Benchmark domains Faster convergence General approach Heterogeneous environments Mapping strategy Model-based reinforcement learning Potential impacts Transfer learning 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	Benchmark domains Faster convergence General approach Heterogeneous environments Mapping strategy Model-based reinforcement learning Potential impacts Transfer learning Numerical Analysis and Scientific Computing
spellingShingle	Benchmark domains Faster convergence General approach Heterogeneous environments Mapping strategy Model-based reinforcement learning Potential impacts Transfer learning Numerical Analysis and Scientific Computing Nguyen, Trung Thanh Silander, Tomi Tze-Yun LEONG, Transferring expectations in model-based reinforcement learning
description	We study how to automatically select and adapt multiple abstractions or representations of the world to support model-based reinforcement learning. We address the challenges of transfer learning in heterogeneous environments with varying tasks. We present an efficient, online framework that, through a sequence of tasks, learns a set of relevant representations to be used in future tasks. Without predefined mapping strategies, we introduce a general approach to support transfer learning across different state spaces. We demonstrate the potential impact of our system through improved jumpstart and faster convergence to near optimum policy in two benchmark domains.
format	text
author	Nguyen, Trung Thanh Silander, Tomi Tze-Yun LEONG,
author_facet	Nguyen, Trung Thanh Silander, Tomi Tze-Yun LEONG,
author_sort	Nguyen, Trung Thanh
title	Transferring expectations in model-based reinforcement learning
title_short	Transferring expectations in model-based reinforcement learning
title_full	Transferring expectations in model-based reinforcement learning
title_fullStr	Transferring expectations in model-based reinforcement learning
title_full_unstemmed	Transferring expectations in model-based reinforcement learning
title_sort	transferring expectations in model-based reinforcement learning
publisher	Institutional Knowledge at Singapore Management University
publishDate	2012
url	https://ink.library.smu.edu.sg/sis_research/3049
_version_	1770572790882107392

Transferring expectations in model-based reinforcement learning

Similar Items