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
Description
Summary: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).