ERA

Download the full-sized PDF of Reinforcement Learning Algorithms for MDPsDownload the full-sized PDF

Analytics

Share

Permanent link (DOI): https://doi.org/10.7939/R3SF2MK09

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)

Reinforcement Learning Algorithms for MDPs Open Access

Descriptions

Author or creator
Szepesvari, Csaba
Additional contributors
Subject/Keyword
Artificial Intelligence
Bias-variance tradeoff
Active learning
Simulation
Reinforcement learning
Stochastic gradient methods
Online learning
Stimulation optimization
Planning
Policy gradient
PAC-learning
Machine Learning
Natural gradient
Overfitting
Q-learning
L:east-sqares methods
Function approximation
Markov decision processes
Stochastic approximation
Two-timescale stochastic approximation
Monte-Carlo methods
Actor-critic methods
Temporal difference learning
Type of item
Computing Science Technical Report
Computing science technical report ID
TR09-13
Language
English
Place
Time
Description
Technical report TR09-13. This article presents a survey of reinforcement learning algorithms for Markov Decision Processes (MDP). In the first half of the article, the problem of value estimation is considered. Here we start by describing the idea of bootstrapping and temporal difference learning. Next, we compare incremental and batch algorithmic variants and discuss the impact of the choice of the function approximation method on the success of learning. In the second half, we describe methods that target the problem of learning to control an MDP. Here online and active learning are discussed first, followed by a description of direct and actor-critic methods.
Date created
2009
DOI
doi:10.7939/R3SF2MK09
License information
Creative Commons Attribution 3.0 Unported
Rights

Citation for previous publication

Source
Link to related item

File Details

Date Uploaded
Date Modified
2014-05-01T00:45:33.584+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: 788894
Last modified: 2015:10:12 20:32:18-06:00
Filename: TR09-13.pdf
Original checksum: f81b17fdc0c07739d1d43852c79ce355
Well formed: false
Valid: false
Status message: Lexical error offset=756574
Page count: 73
Activity of users you follow
User Activity Date