ERA

Download the full-sized PDF of Focus of Attention in Reinforcement LearningDownload the full-sized PDF

Analytics

Share

Permanent link (DOI): https://doi.org/10.7939/R31G0HX9N

Download

Export to: EndNote  |  Zotero  |  Mendeley

Communities

This file is in the following communities:

Computing Science, Department of

Collections

This file is in the following collections:

Technical Reports (Computing Science)

Focus of Attention in Reinforcement Learning Open Access

Descriptions

Author or creator
Li, Lihong
Additional contributors
Subject/Keyword
Reinforcement learning
Focused learning
Reinforcement Learning
State importance
Type of item
Computing Science Technical Report
Computing science technical report ID
TR07-12
Language
English
Place
Time
Description
Technical report TR07-12. One key topic in reinforcement learning is function approximation which is critical for the success of reinforcement learning in domains with large state spaces. Unfortunately, function approximation can lead to several problems including the suboptimality of the produced policies and even divergence of learning. Thus, reinforcement learning with function approximation has remained an area of active research. We demonstrate that in reinforcement learning, it is helpful for the agent to focus on more important states thereby producing better policies using less computing resources. The problem of focused learning is investigated formally, and two classes of reinforcement learning methods are considered: the classification-based approach and the value-function-based approach. For each of these two approaches, we will (i) define a formal metric of state importance, and (ii) utilize it in reinforcement learning with function approximation. The advantages of focusing attention on important states are supported both theoretically and empirically.
Date created
2007
DOI
doi:10.7939/R31G0HX9N
License information
Creative Commons Attribution 3.0 Unported
Rights

Citation for previous publication

Source
Link to related item

File Details

Date Uploaded
Date Modified
2014-04-24T23:48:05.955+00:00
Audit Status
Audits have not yet been run on this file.
Characterization
File format: pdf (Portable Document Format)
Mime type: application/pdf
File size: 3393243
Last modified: 2015:10:12 17:21:59-06:00
Filename: TR07-12.pdf
Original checksum: cd901a97d26f354db11b4680f994680b
Well formed: true
Valid: true
Page count: 112
Activity of users you follow
User Activity Date