Online feature selection for model-based reinforcement learning

We propose a new framework for learning the world dynamics of feature-rich environments in model-based reinforcement learning. The main idea is formalized as a new, factored state-transition representation that supports efficient online-learning of the relevant features. We construct the transition...

Full description

Saved in:
Bibliographic Details
Main Authors: Nguyen, Trung Thanh, Li, Zhuoru, Silander, Tomi, Tze-Yun LEONG
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2013
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/3030
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
id sg-smu-ink.sis_research-4030
record_format dspace
spelling sg-smu-ink.sis_research-40302016-02-05T06:30:05Z Online feature selection for model-based reinforcement learning Nguyen, Trung Thanh Li, Zhuoru Silander, Tomi Tze-Yun LEONG, We propose a new framework for learning the world dynamics of feature-rich environments in model-based reinforcement learning. The main idea is formalized as a new, factored state-transition representation that supports efficient online-learning of the relevant features. We construct the transition models through predicting how the actions change the world. We introduce an online sparse coding learning technique for feature selection in high-dimensional spaces. We derive theoretical guarantees for our framework and empirically demonstrate its practicality in both simulated and real robotics domains. Copyright 2013 by the author(s). 2013-06-21T07:00:00Z text https://ink.library.smu.edu.sg/sis_research/3030 Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Artificial intelligence; Software engineering High dimensional spaces Learning techniques Model-based reinforcement learning Online feature selection Relevant features Theoretical guarantees Transition model World dynamics Databases and Information Systems
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Artificial intelligence; Software engineering High dimensional spaces
Learning techniques
Model-based reinforcement learning
Online feature selection
Relevant features
Theoretical guarantees
Transition model
World dynamics
Databases and Information Systems
spellingShingle Artificial intelligence; Software engineering High dimensional spaces
Learning techniques
Model-based reinforcement learning
Online feature selection
Relevant features
Theoretical guarantees
Transition model
World dynamics
Databases and Information Systems
Nguyen, Trung Thanh
Li, Zhuoru
Silander, Tomi
Tze-Yun LEONG,
Online feature selection for model-based reinforcement learning
description We propose a new framework for learning the world dynamics of feature-rich environments in model-based reinforcement learning. The main idea is formalized as a new, factored state-transition representation that supports efficient online-learning of the relevant features. We construct the transition models through predicting how the actions change the world. We introduce an online sparse coding learning technique for feature selection in high-dimensional spaces. We derive theoretical guarantees for our framework and empirically demonstrate its practicality in both simulated and real robotics domains. Copyright 2013 by the author(s).
format text
author Nguyen, Trung Thanh
Li, Zhuoru
Silander, Tomi
Tze-Yun LEONG,
author_facet Nguyen, Trung Thanh
Li, Zhuoru
Silander, Tomi
Tze-Yun LEONG,
author_sort Nguyen, Trung Thanh
title Online feature selection for model-based reinforcement learning
title_short Online feature selection for model-based reinforcement learning
title_full Online feature selection for model-based reinforcement learning
title_fullStr Online feature selection for model-based reinforcement learning
title_full_unstemmed Online feature selection for model-based reinforcement learning
title_sort online feature selection for model-based reinforcement learning
publisher Institutional Knowledge at Singapore Management University
publishDate 2013
url https://ink.library.smu.edu.sg/sis_research/3030
_version_ 1770572797818437632