Skip to content

V
Variance_Minimiza_ICML
Commit e9f7dd7f by GongYu
Options

最新版VM论文版本—ICML

parents
Showing with 638 additions and 0 deletions
algorithm.sty 0 → 100644
% ALGORITHM STYLE -- Released 8 April 1996
% for LaTeX-2e
% Copyright -- 1994 Peter Williams
% E-mail Peter.Williams@dsto.defence.gov.au
\NeedsTeXFormat{LaTeX2e}
\ProvidesPackage{algorithm}
\typeout{Document Style `algorithm' - floating environment}
\RequirePackage{float}
\RequirePackage{ifthen}
\newcommand{\ALG@within}{nothing}
\newboolean{ALG@within}
\setboolean{ALG@within}{false}
\newcommand{\ALG@floatstyle}{ruled}
\newcommand{\ALG@name}{Algorithm}
\newcommand{\listalgorithmname}{List of \ALG@name s}
% Declare Options
% first appearance
\DeclareOption{plain}{
\renewcommand{\ALG@floatstyle}{plain}
}
\DeclareOption{ruled}{
\renewcommand{\ALG@floatstyle}{ruled}
}
\DeclareOption{boxed}{
\renewcommand{\ALG@floatstyle}{boxed}
}
% then numbering convention
\DeclareOption{part}{
\renewcommand{\ALG@within}{part}
\setboolean{ALG@within}{true}
}
\DeclareOption{chapter}{
\renewcommand{\ALG@within}{chapter}
\setboolean{ALG@within}{true}
}
\DeclareOption{section}{
\renewcommand{\ALG@within}{section}
\setboolean{ALG@within}{true}
}
\DeclareOption{subsection}{
\renewcommand{\ALG@within}{subsection}
\setboolean{ALG@within}{true}
}
\DeclareOption{subsubsection}{
\renewcommand{\ALG@within}{subsubsection}
\setboolean{ALG@within}{true}
}
\DeclareOption{nothing}{
\renewcommand{\ALG@within}{nothing}
\setboolean{ALG@within}{true}
}
\DeclareOption*{\edef\ALG@name{\CurrentOption}}
% ALGORITHM
%
\ProcessOptions
\floatstyle{\ALG@floatstyle}
\ifthenelse{\boolean{ALG@within}}{
\ifthenelse{\equal{\ALG@within}{part}}
{\newfloat{algorithm}{htbp}{loa}[part]}{}
\ifthenelse{\equal{\ALG@within}{chapter}}
{\newfloat{algorithm}{htbp}{loa}[chapter]}{}
\ifthenelse{\equal{\ALG@within}{section}}
{\newfloat{algorithm}{htbp}{loa}[section]}{}
\ifthenelse{\equal{\ALG@within}{subsection}}
{\newfloat{algorithm}{htbp}{loa}[subsection]}{}
\ifthenelse{\equal{\ALG@within}{subsubsection}}
{\newfloat{algorithm}{htbp}{loa}[subsubsection]}{}
\ifthenelse{\equal{\ALG@within}{nothing}}
{\newfloat{algorithm}{htbp}{loa}}{}
}{
\newfloat{algorithm}{htbp}{loa}
}
\floatname{algorithm}{\ALG@name}
\newcommand{\listofalgorithms}{\listof{algorithm}{\listalgorithmname}}
algorithmic.sty 0 → 100644
% ALGORITHMIC STYLE -- Released 8 APRIL 1996
% for LaTeX version 2e
% Copyright -- 1994 Peter Williams
% E-mail PeterWilliams@dsto.defence.gov.au
%
% Modified by Alex Smola (08/2000)
% E-mail Alex.Smola@anu.edu.au
%
\NeedsTeXFormat{LaTeX2e}
\ProvidesPackage{algorithmic}
\typeout{Document Style `algorithmic' - environment}
%
\RequirePackage{ifthen}
\RequirePackage{calc}
\newboolean{ALC@noend}
\setboolean{ALC@noend}{false}
\newcounter{ALC@line}
\newcounter{ALC@rem}
\newlength{\ALC@tlm}
%
\DeclareOption{noend}{\setboolean{ALC@noend}{true}}
%
\ProcessOptions
%
% ALGORITHMIC
\newcommand{\algorithmicrequire}{\textbf{Require:}}
\newcommand{\algorithmicensure}{\textbf{Ensure:}}
\newcommand{\algorithmiccomment}[1]{\{#1\}}
\newcommand{\algorithmicend}{\textbf{end}}
\newcommand{\algorithmicif}{\textbf{if}}
\newcommand{\algorithmicthen}{\textbf{then}}
\newcommand{\algorithmicelse}{\textbf{else}}
\newcommand{\algorithmicelsif}{\algorithmicelse\ \algorithmicif}
\newcommand{\algorithmicendif}{\algorithmicend\ \algorithmicif}
\newcommand{\algorithmicfor}{\textbf{for}}
\newcommand{\algorithmicforall}{\textbf{for all}}
\newcommand{\algorithmicdo}{\textbf{do}}
\newcommand{\algorithmicendfor}{\algorithmicend\ \algorithmicfor}
\newcommand{\algorithmicwhile}{\textbf{while}}
\newcommand{\algorithmicendwhile}{\algorithmicend\ \algorithmicwhile}
\newcommand{\algorithmicloop}{\textbf{loop}}
\newcommand{\algorithmicendloop}{\algorithmicend\ \algorithmicloop}
\newcommand{\algorithmicrepeat}{\textbf{repeat}}
\newcommand{\algorithmicuntil}{\textbf{until}}
%changed by alex smola
\newcommand{\algorithmicinput}{\textbf{input}}
\newcommand{\algorithmicoutput}{\textbf{output}}
\newcommand{\algorithmicset}{\textbf{set}}
\newcommand{\algorithmictrue}{\textbf{true}}
\newcommand{\algorithmicfalse}{\textbf{false}}
\newcommand{\algorithmicand}{\textbf{and\ }}
\newcommand{\algorithmicor}{\textbf{or\ }}
\newcommand{\algorithmicfunction}{\textbf{function}}
\newcommand{\algorithmicendfunction}{\algorithmicend\ \algorithmicfunction}
\newcommand{\algorithmicmain}{\textbf{main}}
\newcommand{\algorithmicendmain}{\algorithmicend\ \algorithmicmain}
%end changed by alex smola
\def\ALC@item[#1]{%
\if@noparitem \@donoparitem
\else \if@inlabel \indent \par \fi
\ifhmode \unskip\unskip \par \fi
\if@newlist \if@nobreak \@nbitem \else
\addpenalty\@beginparpenalty
\addvspace\@topsep \addvspace{-\parskip}\fi
\else \addpenalty\@itempenalty \addvspace\itemsep
\fi
\global\@inlabeltrue
\fi
\everypar{\global\@minipagefalse\global\@newlistfalse
\if@inlabel\global\@inlabelfalse \hskip -\parindent \box\@labels
\penalty\z@ \fi
\everypar{}}\global\@nobreakfalse
\if@noitemarg \@noitemargfalse \if@nmbrlist \refstepcounter{\@listctr}\fi \fi
\sbox\@tempboxa{\makelabel{#1}}%
\global\setbox\@labels
\hbox{\unhbox\@labels \hskip \itemindent
\hskip -\labelwidth \hskip -\ALC@tlm
\ifdim \wd\@tempboxa >\labelwidth
\box\@tempboxa
\else \hbox to\labelwidth {\unhbox\@tempboxa}\fi
\hskip \ALC@tlm}\ignorespaces}
%
\newenvironment{algorithmic}[1][0]{
\let\@item\ALC@item
\newcommand{\ALC@lno}{%
\ifthenelse{\equal{\arabic{ALC@rem}}{0}}
{{\footnotesize \arabic{ALC@line}:}}{}%
}
\let\@listii\@listi
\let\@listiii\@listi
\let\@listiv\@listi
\let\@listv\@listi
\let\@listvi\@listi
\let\@listvii\@listi
\newenvironment{ALC@g}{
\begin{list}{\ALC@lno}{ \itemsep\z@ \itemindent\z@
\listparindent\z@ \rightmargin\z@
\topsep\z@ \partopsep\z@ \parskip\z@\parsep\z@
\leftmargin 1em
\addtolength{\ALC@tlm}{\leftmargin}
}
}
{\end{list}}
\newcommand{\ALC@it}{\addtocounter{ALC@line}{1}\addtocounter{ALC@rem}{1}\ifthenelse{\equal{\arabic{ALC@rem}}{#1}}{\setcounter{ALC@rem}{0}}{}\item}
\newcommand{\ALC@com}[1]{\ifthenelse{\equal{##1}{default}}%
{}{\ \algorithmiccomment{##1}}}
\newcommand{\REQUIRE}{\item[\algorithmicrequire]}
\newcommand{\ENSURE}{\item[\algorithmicensure]}
\newcommand{\STATE}{\ALC@it}
\newcommand{\COMMENT}[1]{\algorithmiccomment{##1}}
%changes by alex smola
\newcommand{\INPUT}{\item[\algorithmicinput]}
\newcommand{\OUTPUT}{\item[\algorithmicoutput]}
\newcommand{\SET}{\item[\algorithmicset]}
% \newcommand{\TRUE}{\algorithmictrue}
% \newcommand{\FALSE}{\algorithmicfalse}
\newcommand{\AND}{\algorithmicand}
\newcommand{\OR}{\algorithmicor}
\newenvironment{ALC@func}{\begin{ALC@g}}{\end{ALC@g}}
\newenvironment{ALC@main}{\begin{ALC@g}}{\end{ALC@g}}
%end changes by alex smola
\newenvironment{ALC@if}{\begin{ALC@g}}{\end{ALC@g}}
\newenvironment{ALC@for}{\begin{ALC@g}}{\end{ALC@g}}
\newenvironment{ALC@whl}{\begin{ALC@g}}{\end{ALC@g}}
\newenvironment{ALC@loop}{\begin{ALC@g}}{\end{ALC@g}}
\newenvironment{ALC@rpt}{\begin{ALC@g}}{\end{ALC@g}}
\renewcommand{\\}{\@centercr}
\newcommand{\IF}[2][default]{\ALC@it\algorithmicif\ ##2\ \algorithmicthen%
\ALC@com{##1}\begin{ALC@if}}
\newcommand{\SHORTIF}[2]{\ALC@it\algorithmicif\ ##1\
\algorithmicthen\ {##2}}
\newcommand{\ELSE}[1][default]{\end{ALC@if}\ALC@it\algorithmicelse%
\ALC@com{##1}\begin{ALC@if}}
\newcommand{\ELSIF}[2][default]%
{\end{ALC@if}\ALC@it\algorithmicelsif\ ##2\ \algorithmicthen%
\ALC@com{##1}\begin{ALC@if}}
\newcommand{\FOR}[2][default]{\ALC@it\algorithmicfor\ ##2\ \algorithmicdo%
\ALC@com{##1}\begin{ALC@for}}
\newcommand{\FORALL}[2][default]{\ALC@it\algorithmicforall\ ##2\ %
\algorithmicdo%
\ALC@com{##1}\begin{ALC@for}}
\newcommand{\SHORTFORALL}[2]{\ALC@it\algorithmicforall\ ##1\ %
\algorithmicdo\ {##2}}
\newcommand{\WHILE}[2][default]{\ALC@it\algorithmicwhile\ ##2\ %
\algorithmicdo%
\ALC@com{##1}\begin{ALC@whl}}
\newcommand{\LOOP}[1][default]{\ALC@it\algorithmicloop%
\ALC@com{##1}\begin{ALC@loop}}
%changed by alex smola
\newcommand{\FUNCTION}[2][default]{\ALC@it\algorithmicfunction\ ##2\ %
\ALC@com{##1}\begin{ALC@func}}
\newcommand{\MAIN}[2][default]{\ALC@it\algorithmicmain\ ##2\ %
\ALC@com{##1}\begin{ALC@main}}
%end changed by alex smola
\newcommand{\REPEAT}[1][default]{\ALC@it\algorithmicrepeat%
\ALC@com{##1}\begin{ALC@rpt}}
\newcommand{\UNTIL}[1]{\end{ALC@rpt}\ALC@it\algorithmicuntil\ ##1}
\ifthenelse{\boolean{ALC@noend}}{
\newcommand{\ENDIF}{\end{ALC@if}}
\newcommand{\ENDFOR}{\end{ALC@for}}
\newcommand{\ENDWHILE}{\end{ALC@whl}}
\newcommand{\ENDLOOP}{\end{ALC@loop}}
\newcommand{\ENDFUNCTION}{\end{ALC@func}}
\newcommand{\ENDMAIN}{\end{ALC@main}}
}{
\newcommand{\ENDIF}{\end{ALC@if}\ALC@it\algorithmicendif}
\newcommand{\ENDFOR}{\end{ALC@for}\ALC@it\algorithmicendfor}
\newcommand{\ENDWHILE}{\end{ALC@whl}\ALC@it\algorithmicendwhile}
\newcommand{\ENDLOOP}{\end{ALC@loop}\ALC@it\algorithmicendloop}
\newcommand{\ENDFUNCTION}{\end{ALC@func}\ALC@it\algorithmicendfunction}
\newcommand{\ENDMAIN}{\end{ALC@main}\ALC@it\algorithmicendmain}
}
\renewcommand{\@toodeep}{}
\begin{list}{\ALC@lno}{\setcounter{ALC@line}{0}\setcounter{ALC@rem}{0}%
\itemsep\z@ \itemindent\z@ \listparindent\z@%
\partopsep\z@ \parskip\z@ \parsep\z@%
\labelsep 0.5em \topsep 0.2em%
\ifthenelse{\equal{#1}{0}}
{\labelwidth 0.5em }
{\labelwidth 1.2em }
\leftmargin\labelwidth \addtolength{\leftmargin}{\labelsep}
\ALC@tlm\labelsep
}
}
{\end{list}}
example_paper.bbl 0 → 100644
\begin{thebibliography}{34}
\providecommand{\natexlab}[1]{#1}
\providecommand{\url}[1]{\texttt{#1}}
\expandafter\ifx\csname urlstyle\endcsname\relax
\providecommand{\doi}[1]{doi: #1}\else
\providecommand{\doi}{doi: \begingroup \urlstyle{rm}\Url}\fi
\bibitem[Baird et~al.(1995)]{baird1995residual}
Baird, L. et~al.
\newblock Residual algorithms: Reinforcement learning with function approximation.
\newblock In \emph{Proc. 12th Int. Conf. Mach. Learn.}, pp.\ 30--37, 1995.
\bibitem[Bas-Serrano et~al.(2021)Bas-Serrano, Curi, Krause, and Neu]{basserrano2021logistic}
Bas-Serrano, J., Curi, S., Krause, A., and Neu, G.
\newblock Logistic q-learning.
\newblock In \emph{International Conference on Artificial Intelligence and Statistics}, pp.\ 3610--3618, 2021.
\bibitem[Borkar(1997)]{borkar1997stochastic}
Borkar, V.~S.
\newblock Stochastic approximation with two time scales.
\newblock \emph{Syst. \& Control Letters}, 29\penalty0 (5):\penalty0 291--294, 1997.
\bibitem[Borkar \& Meyn(2000)Borkar and Meyn]{borkar2000ode}
Borkar, V.~S. and Meyn, S.~P.
\newblock The ode method for convergence of stochastic approximation and reinforcement learning.
\newblock \emph{SIAM J. Control Optim.}, 38\penalty0 (2):\penalty0 447--469, 2000.
\bibitem[Chen et~al.(2023)Chen, Ma, Li, Yang, Yang, and Gao]{chen2023modified}
Chen, X., Ma, X., Li, Y., Yang, G., Yang, S., and Gao, Y.
\newblock Modified retrace for off-policy temporal difference learning.
\newblock In \emph{Uncertainty in Artificial Intelligence}, pp.\ 303--312. PMLR, 2023.
\bibitem[Dalal et~al.(2020)Dalal, Szorenyi, and Thoppe]{dalal2020tale}
Dalal, G., Szorenyi, B., and Thoppe, G.
\newblock A tale of two-timescale reinforcement learning with the tightest finite-time bound.
\newblock In \emph{Proceedings of the AAAI Conference on Artificial Intelligence}, volume~34, pp.\ 3701--3708, 2020.
\bibitem[Devlin \& Kudenko(2012)Devlin and Kudenko]{devlin2012dynamic}
Devlin, S. and Kudenko, D.
\newblock Dynamic potential-based reward shaping.
\newblock In \emph{Proc. 11th Int. Conf. Autonomous Agents and Multiagent Systems}, pp.\ 433--440, 2012.
\bibitem[Feng et~al.(2019)Feng, Li, and Liu]{feng2019kernel}
Feng, Y., Li, L., and Liu, Q.
\newblock A kernel loss for solving the bellman equation.
\newblock In \emph{Advances in Neural Information Processing Systems}, pp.\ 15430--15441, 2019.
\bibitem[Givchi \& Palhang(2015)Givchi and Palhang]{givchi2015quasi}
Givchi, A. and Palhang, M.
\newblock Quasi newton temporal difference learning.
\newblock In \emph{Asian Conference on Machine Learning}, pp.\ 159--172, 2015.
\bibitem[Hackman(2012)]{hackman2012faster}
Hackman, L.
\newblock \emph{Faster Gradient-TD Algorithms}.
\newblock PhD thesis, University of Alberta, 2012.
\bibitem[Hallak et~al.(2016)Hallak, Tamar, Munos, and Mannor]{hallak2016generalized}
Hallak, A., Tamar, A., Munos, R., and Mannor, S.
\newblock Generalized emphatic temporal difference learning: bias-variance analysis.
\newblock In \emph{Proceedings of the 30th AAAI Conference on Artificial Intelligence}, pp.\ 1631--1637, 2016.
\bibitem[Hirsch(1989)]{hirsch1989convergent}
Hirsch, M.~W.
\newblock Convergent activation dynamics in continuous time networks.
\newblock \emph{Neural Netw.}, 2\penalty0 (5):\penalty0 331--349, 1989.
\bibitem[Johnson \& Zhang(2013)Johnson and Zhang]{johnson2013accelerating}
Johnson, R. and Zhang, T.
\newblock Accelerating stochastic gradient descent using predictive variance reduction.
\newblock In \emph{Advances in Neural Information Processing Systems}, pp.\ 315--323, 2013.
\bibitem[Korda \& La(2015)Korda and La]{korda2015td}
Korda, N. and La, P.
\newblock On td (0) with function approximation: Concentration bounds and a centered variant with exponential convergence.
\newblock In \emph{International conference on machine learning}, pp.\ 626--634. PMLR, 2015.
\bibitem[Langley(2000)]{langley00}
Langley, P.
\newblock Crafting papers on machine learning.
\newblock In Langley, P. (ed.), \emph{Proceedings of the 17th International Conference on Machine Learning (ICML 2000)}, pp.\ 1207--1216, Stanford, CA, 2000. Morgan Kaufmann.
\bibitem[Liu et~al.(2015)Liu, Liu, Ghavamzadeh, Mahadevan, and Petrik]{liu2015finite}
Liu, B., Liu, J., Ghavamzadeh, M., Mahadevan, S., and Petrik, M.
\newblock Finite-sample analysis of proximal gradient td algorithms.
\newblock In \emph{Proceedings of the 21st Conference on Uncertainty in Artificial Intelligence}, pp.\ 504--513, 2015.
\bibitem[Liu et~al.(2016)Liu, Liu, Ghavamzadeh, Mahadevan, and Petrik]{liu2016proximal}
Liu, B., Liu, J., Ghavamzadeh, M., Mahadevan, S., and Petrik, M.
\newblock Proximal gradient temporal difference learning algorithms.
\newblock In \emph{Proceedings of the International Joint Conference on Artificial Intelligence}, pp.\ 4195--4199, 2016.
\bibitem[Liu et~al.(2018)Liu, Gemp, Ghavamzadeh, Liu, Mahadevan, and Petrik]{liu2018proximal}
Liu, B., Gemp, I., Ghavamzadeh, M., Liu, J., Mahadevan, S., and Petrik, M.
\newblock Proximal gradient temporal difference learning: Stable reinforcement learning with polynomial sample complexity.
\newblock \emph{Journal of Artificial Intelligence Research}, 63:\penalty0 461--494, 2018.
\bibitem[Maei(2011)]{maei2011gradient}
Maei, H.~R.
\newblock \emph{Gradient temporal-difference learning algorithms}.
\newblock PhD thesis, University of Alberta, 2011.
\bibitem[Ng et~al.(1999)Ng, Harada, and Russell]{ng1999policy}
Ng, A.~Y., Harada, D., and Russell, S.
\newblock Policy invariance under reward transformations: Theory and application to reward shaping.
\newblock In \emph{Proc. 16th Int. Conf. Mach. Learn.}, pp.\ 278--287, 1999.
\bibitem[Pan et~al.(2017)Pan, White, and White]{pan2017accelerated}
Pan, Y., White, A., and White, M.
\newblock Accelerated gradient temporal difference learning.
\newblock In \emph{Proceedings of the 21st AAAI Conference on Artificial Intelligence}, pp.\ 2464--2470, 2017.
\bibitem[Schulman et~al.(2015)Schulman, Levine, Abbeel, Jordan, and Moritz]{schulman2015trust}
Schulman, J., Levine, S., Abbeel, P., Jordan, M., and Moritz, P.
\newblock Trust region policy optimization.
\newblock In \emph{International Conference on Machine Learning}, pp.\ 1889--1897, 2015.
\bibitem[Schulman et~al.(2017)Schulman, Wolski, Dhariwal, Radford, and Klimov]{schulman2017proximal}
Schulman, J., Wolski, F., Dhariwal, P., Radford, A., and Klimov, O.
\newblock Proximal policy optimization algorithms.
\newblock \emph{arXiv preprint arXiv:1707.06347}, 2017.
\bibitem[Schwartz(1993)]{schwartz1993reinforcement}
Schwartz, A.
\newblock A reinforcement learning method for maximizing undiscounted rewards.
\newblock In \emph{Proc. 10th Int. Conf. Mach. Learn.}, volume 298, pp.\ 298--305, 1993.
\bibitem[Sutton et~al.(2009)Sutton, Maei, Precup, Bhatnagar, Silver, Szepesv{\'a}ri, and Wiewiora]{sutton2009fast}
Sutton, R., Maei, H., Precup, D., Bhatnagar, S., Silver, D., Szepesv{\'a}ri, C., and Wiewiora, E.
\newblock Fast gradient-descent methods for temporal-difference learning with linear function approximation.
\newblock In \emph{Proc. 26th Int. Conf. Mach. Learn.}, pp.\ 993--1000, 2009.
\bibitem[Sutton(1988)]{sutton1988learning}
Sutton, R.~S.
\newblock Learning to predict by the methods of temporal differences.
\newblock \emph{Machine learning}, 3\penalty0 (1):\penalty0 9--44, 1988.
\bibitem[Sutton \& Barto(2018)Sutton and Barto]{Sutton2018book}
Sutton, R.~S. and Barto, A.~G.
\newblock \emph{Reinforcement Learning: An Introduction}.
\newblock The MIT Press, second edition, 2018.
\bibitem[Sutton et~al.(2008)Sutton, Maei, and Szepesv{\'a}ri]{sutton2008convergent}
Sutton, R.~S., Maei, H.~R., and Szepesv{\'a}ri, C.
\newblock A convergent $ o (n) $ temporal-difference algorithm for off-policy learning with linear function approximation.
\newblock In \emph{Advances in Neural Information Processing Systems}, pp.\ 1609--1616. Cambridge, MA: MIT Press, 2008.
\bibitem[Sutton et~al.(2016)Sutton, Mahmood, and White]{sutton2016emphatic}
Sutton, R.~S., Mahmood, A.~R., and White, M.
\newblock An emphatic approach to the problem of off-policy temporal-difference learning.
\newblock \emph{The Journal of Machine Learning Research}, 17\penalty0 (1):\penalty0 2603--2631, 2016.
\bibitem[Tsitsiklis \& Van~Roy(1997)Tsitsiklis and Van~Roy]{tsitsiklis1997analysis}
Tsitsiklis, J.~N. and Van~Roy, B.
\newblock Analysis of temporal-diffference learning with function approximation.
\newblock In \emph{Advances in Neural Information Processing Systems}, pp.\ 1075--1081, 1997.
\bibitem[Xu et~al.(2019)Xu, Wang, Zhou, and Liang]{xu2019reanalysis}
Xu, T., Wang, Z., Zhou, Y., and Liang, Y.
\newblock Reanalysis of variance reduced temporal difference learning.
\newblock In \emph{International Conference on Learning Representations}, 2019.
\bibitem[Xu et~al.(2020)Xu, Wang, Zhou, and Liang]{xu2020reanalysis}
Xu, T., Wang, Z., Zhou, Y., and Liang, Y.
\newblock Reanalysis of variance reduced temporal difference learning.
\newblock \emph{arXiv preprint arXiv:2001.01898}, 2020.
\bibitem[Zhang \& Whiteson(2022)Zhang and Whiteson]{zhang2022truncated}
Zhang, S. and Whiteson, S.
\newblock Truncated emphatic temporal difference methods for prediction and control.
\newblock \emph{The Journal of Machine Learning Research}, 23\penalty0 (1):\penalty0 6859--6917, 2022.
\bibitem[Zhou(2021)]{zhou2021machine}
Zhou, Z.-H.
\newblock \emph{Machine learning}.
\newblock Springer Nature, 2021.
\end{thebibliography}
example_paper.blg 0 → 100644
This is BibTeX, Version 0.99d (TeX Live 2023)
Capacity: max_strings=200000, hash_size=200000, hash_prime=170003
The top-level auxiliary file: example_paper.aux
The style file: icml2024.bst
Database file #1: example_paper.bib
Warning--can't use both volume and number fields in dalal2020tale
You've used 34 entries,
2773 wiz_defined-function locations,
790 strings with 10645 characters,
and the built_in function-call counts, 19097 in all, are:
= -- 1771
> -- 980
< -- 39
+ -- 332
- -- 298
* -- 1422
:= -- 2705
add.period$ -- 106
call.type$ -- 34
change.case$ -- 197
chr.to.int$ -- 34
cite$ -- 69
duplicate$ -- 950
empty$ -- 1596
format.name$ -- 349
if$ -- 4208
int.to.chr$ -- 1
int.to.str$ -- 1
missing$ -- 34
newline$ -- 178
num.names$ -- 138
pop$ -- 445
preamble$ -- 1
purify$ -- 166
quote$ -- 0
skip$ -- 806
stack$ -- 0
substring$ -- 965
swap$ -- 257
text.length$ -- 22
text.prefix$ -- 0
top$ -- 0
type$ -- 364
warning$ -- 1
while$ -- 176
width$ -- 0
write$ -- 452
(There was 1 warning)
fancyhdr.sty 0 → 100644
This diff is collapsed. Click to expand it.
icml2024.bst 0 → 100644
This diff is collapsed. Click to expand it.
icml2024.sty 0 → 100644
This diff is collapsed. Click to expand it.
pic/BairdExample.tex 0 → 100644
\resizebox{7cm}{4.4cm}{
\begin{tikzpicture}[smooth]
\node[coordinate] (origin) at (0.3,0) {};
\node[coordinate] (num7) at (3,0) {};
\node[coordinate] (num1) at (1,2.5) {};
\path (num7) ++ (-10:0.5cm) node (num7_bright1) [coordinate] {};
\path (num7) ++ (-30:0.7cm) node (num7_bright2) [coordinate] {};
\path (num7) ++ (-60:0.35cm) node (num7_bright3) [coordinate] {};
\path (num7) ++ (-60:0.6cm) node (num7_bright4) [coordinate] {};
\path (origin) ++ (90:3cm) node (origin_above) [coordinate] {};
\path (origin_above) ++ (0:5.7cm) node (origin_aright) [coordinate] {};
\path (num1) ++ (90:0.5cm) node (num1_a) [coordinate] {};
\path (num1) ++ (-90:0.3cm) node (num1_b) [coordinate] {};
\path (num1) ++ (0:1cm) node (num2) [coordinate] {};
\path (num1_a) ++ (0:1cm) node (num2_a) [coordinate] {};
\path (num1_b) ++ (0:1cm) node (num2_b) [coordinate] {};
\path (num2) ++ (0:1cm) node (num3) [coordinate] {};
\path (num2_a) ++ (0:1cm) node (num3_a) [coordinate] {};
\path (num2_b) ++ (0:1cm) node (num3_b) [coordinate] {};
\path (num3) ++ (0:1cm) node (num4) [coordinate] {};
\path (num3_a) ++ (0:1cm) node (num4_a) [coordinate] {};
\path (num3_b) ++ (0:1cm) node (num4_b) [coordinate] {};
\path (num4) ++ (0:1cm) node (num5) [coordinate] {};
\path (num4_a) ++ (0:1cm) node (num5_a) [coordinate] {};
\path (num4_b) ++ (0:1cm) node (num5_b) [coordinate] {};
\path (num5) ++ (0:1cm) node (num6) [coordinate] {};
\path (num5_a) ++ (0:1cm) node (num6_a) [coordinate] {};
\path (num5_b) ++ (0:1cm) node (num6_b) [coordinate] {};
%\draw[->](0,0) -- (1,1);
%\draw[dashed,line width = 0.03cm] (0,0) -- (1,1);
%\fill (0.5,0.5) circle (0.5);
%\draw[shape=circle,fill=white,draw=black] (a) at (num7) {7};
\draw[dashed,line width = 0.03cm,xshift=3cm] plot[tension=0.06]
coordinates{(num7) (origin) (origin_above) (origin_aright)};
\draw[->,>=stealth,line width = 0.02cm,xshift=3cm] plot[tension=0.5]
coordinates{(num7) (num7_bright1) (num7_bright2)(num7_bright4) (num7_bright3)};
\node[line width = 0.02cm,shape=circle,fill=white,draw=black] (g) at (num7) {7};
\draw[<->,>=stealth,dashed,line width = 0.03cm,] (num1) -- (num1_a) ;
\node[line width = 0.02cm,shape=circle,fill=white,draw=black] (a) at (num1_b) {1};
\draw[<->,>=stealth,dashed,line width = 0.03cm,] (num2) -- (num2_a) ;
\node[line width = 0.02cm,shape=circle,fill=white,draw=black] (b) at (num2_b) {2};
\draw[<->,>=stealth,dashed,line width = 0.03cm,] (num3) -- (num3_a) ;
\node[line width = 0.02cm,shape=circle,fill=white,draw=black] (c) at (num3_b) {3};
\draw[<->,>=stealth,dashed,line width = 0.03cm,] (num4) -- (num4_a) ;
\node[line width = 0.02cm,shape=circle,fill=white,draw=black] (d) at (num4_b) {4};
\draw[<->,>=stealth,dashed,line width = 0.03cm,] (num5) -- (num5_a) ;
\node[line width = 0.02cm,shape=circle,fill=white,draw=black] (e) at (num5_b) {5};
\draw[<->,>=stealth,dashed,line width = 0.03cm,] (num6) -- (num6_a) ;
\node[line width = 0.02cm,shape=circle,fill=white,draw=black] (f) at (num6_b) {6};
\draw[->,>=stealth,line width = 0.02cm] (a)--(g);
\draw[->,>=stealth,line width = 0.02cm] (b)--(g);
\draw[->,>=stealth,line width = 0.02cm] (c)--(g);
\draw[->,>=stealth,line width = 0.02cm] (d)--(g);
\draw[->,>=stealth,line width = 0.02cm] (e)--(g);
\draw[->,>=stealth,line width = 0.02cm] (f)--(g);
\end{tikzpicture}
}
pic/randomwalk.tex 0 → 100644
% \tikzstyle{int}=[draw, fill=blue!20, minimum size=2em]
% \tikzstyle{block}=[draw, fill=gray, minimum size=1.5em]
% \tikzstyle{init} = [pin edge={to-,thin,black}]
% \resizebox{8cm}{1.2cm}{
% \begin{tikzpicture}[node distance=1.5cm,auto,>=latex']
% \node [block] (o) {};
% \node (p) [left of=o,node distance=0.5cm, coordinate] {o};
% \node [shape=circle,int] (a) [right of=o]{$A$};
% \node (b) [left of=a,node distance=1.5cm, coordinate] {a};
% \node [shape=circle,int] (c) [right of=a] {$B$};
% \node (d) [left of=c,node distance=1.5cm, coordinate] {c};
% \node [shape=circle,int, pin={[init]above:$$}] (e) [right of=c]{$C$};
% \node (f) [left of=e,node distance=1.5cm, coordinate] {e};
% \node [shape=circle,int] (g) [right of=e] {$D$};
% \node (h) [left of=g,node distance=1.5cm, coordinate] {g};
% \node [shape=circle,int] (i) [right of=g] {$E$};
% \node (j) [left of=i,node distance=1.5cm, coordinate] {i};
% \node [block] (k) [right of=i] {};
% \node (l) [left of=k,node distance=0.5cm, coordinate] {k};
% \path[<-] (o) edge node {$0$} (a);
% \path[<->] (a) edge node {$0$} (c);
% \path[<->] (c) edge node {$0$} (e);
% \path[<->] (e) edge node {$0$} (g);
% \path[<->] (g) edge node {$0$} (i);
% \draw[->] (i) edge node {$1$} (k);
% \end{tikzpicture}
% }
\tikzstyle{int}=[draw, fill=blue!20, minimum size=2em]
\tikzstyle{block}=[draw, fill=gray, minimum size=1.5em]
\tikzstyle{init} = [pin edge={to-,thin,black}]
\resizebox{8cm}{1.5cm}{
\begin{tikzpicture}[node distance=1.5cm, auto, >=latex]
\node [block] (o) {};
\node (p) [left of=o, node distance=0.5cm, coordinate] {o};
\node [shape=circle, int] (a) [right of=o] {$A$};
\node (b) [left of=a, node distance=1.5cm, coordinate] {a};
\node [shape=circle, int] (c) [right of=a] {$B$};
\node (d) [left of=c, node distance=1.5cm, coordinate] {c};
\node [shape=circle, int, pin={[init]above:$ $}] (e) [right of=c] {$C$};
\node (f) [left of=e, node distance=1.5cm, coordinate] {e};
\node [shape=circle, int] (g) [right of=e] {$D$};
\node (h) [left of=g, node distance=1.5cm, coordinate] {g};
\node [shape=circle, int] (i) [right of=g] {$E$};
\node (j) [left of=i, node distance=1.5cm, coordinate] {i};
\node [block] (k) [right of=i] {};
\node (l) [left of=k, node distance=0.5cm, coordinate] {k};
\path[->] (o) edge node {$0$} (a);
\path[<->] (a) edge node {$0$} (c);
\path[<->] (c) edge node {$0$} (e);
\path[<->] (e) edge node {$0$} (g);
\path[<->] (g) edge node {$0$} (i);
\draw[->] (i) edge node {$1$} (k);
\end{tikzpicture}
}
\ No newline at end of file
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment