Re: AI research - reinforcement learning

--===============5625410955837368765==
Content-Type: multipart/alternative; boundary=0015175cfe80a8dcf804daf419c4

--0015175cfe80a8dcf804daf419c4
Content-Type: text/plain; charset=ISO-8859-1

Dear Walter,

Bernhard already pointed you in the right direction.

I wuold just want to add few information.
In the literature, especially in the CIG (Computational Intelligence in
Games) research area, there are several works about applying machine
learning and evolutionary computation to TORCS.
Most of this works apply evolutionary computation techniques, but you can
find also some RL applications (e.g., our work at CEC 2010:
http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=5586191&tag=1).

Concerning the software, we built an API on top of TORCS to run a
scientific competition. You could have a look to the page of this year
competition: scr.geccocompetitions.com and, maybe, have a look to the
papers about Simulated Car Racing competition published in the past years.

Best,
Daniele



On Mon, Apr 22, 2013 at 7:22 AM, Bernhard Wymann <[email protected]> wrote:

> Hi Walter
>
> Maybe you found it already, but I can give you some pointers:
> - http://scr.geccocompetitions.com/previous-scr/ (I think there is one
> little "paper" available for each submitted opponent)
> - Google/ Google Scholar
> http://scholar.google.com/scholar?q=torcs+car+reinforcement
> - http://groups.google.com/forum/#!forum/racingcompetition
> - You can search as well torcs-users/devel with sf.net
> http://sourceforge.net/p/torcs/mailman/?source=navbar
>
> Not about learning, but about using TORCS:
> http://www.youtube.com/playlist?list=PLq-L0hhLuRI23uh_HvNTnOD07esKsZkrt
>
> Other experiences and thoughts?
>
> Best regards
>
> Bernhard
>
>
> On 04/22/2013 05:37 AM, jlwalter wrote:
> > Hello everyone,
> >
> > My name is Jeremiah and I'm starting a research project on Reinforcement
> > Learning testing different algorithms' effectiveness at 'learning to
> > drive', or dealing with continuous actions. And I'm going to use TORCS
> > as my simulation!
> >
> > So my question is, has anyone done any similar Reinforcement Learning
> > research and have you any tips or recommendations when it comes to
> > setting the simulation environment up?
> > I appreciate any help I can get!
> >
> > Thankyou,
> > Jeremiah Walter
> > BComp, University of Tasmania
> >
> >
> >
> ------------------------------------------------------------------------------
> > Precog is a next-generation analytics platform capable of advanced
> > analytics on semi-structured data. The platform includes APIs for
> building
> > apps and a phenomenal toolset for data science. Developers can use
> > our toolset for easy data analysis & visualization. Get a free account!
> > http://www2.precog.com/precogplatform/slashdotnewsletter
> >
> >
> >
> > _______________________________________________
> > Torcs-devel mailing list
> > [email protected]
> > https://lists.sourceforge.net/lists/listinfo/torcs-devel
> >
>
>
>
> ------------------------------------------------------------------------------
> Precog is a next-generation analytics platform capable of advanced
> analytics on semi-structured data. The platform includes APIs for building
> apps and a phenomenal toolset for data science. Developers can use
> our toolset for easy data analysis & visualization. Get a free account!
> http://www2.precog.com/precogplatform/slashdotnewsletter
> _______________________________________________
> Torcs-devel mailing list
> [email protected]
> https://lists.sourceforge.net/lists/listinfo/torcs-devel
>

--0015175cfe80a8dcf804daf419c4
Content-Type: text/html; charset=ISO-8859-1
Content-Transfer-Encoding: quoted-printable

<div dir=3D"ltr">Dear Walter,<div><br></div><div>Bernhard already pointed y=
ou in the right direction.</div><div><br></div><div style>I wuold just want=
 to add few information.=A0</div><div style>In the literature, especially i=
n the CIG (Computational Intelligence in Games) research area, there are se=
veral works about applying machine learning and evolutionary computation to=
 TORCS.</div>
<div style>Most of this works apply evolutionary computation techniques, bu=
t you can find also some RL applications (e.g., our work at CEC 2010:=A0<a =
href=3D"http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=3D5586191&amp;=
tag=3D1">http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=3D5586191&amp=
;tag=3D1</a>).</div>
<div style><br></div><div style>Concerning the software, we built an API on=
 top of TORCS to run a scientific competition. You could have a look to the=
 page of this year competition: <a href=3D"http://scr.geccocompetitions.com=
">scr.geccocompetitions.com</a> and, maybe, have a look to the papers about=
 Simulated Car Racing competition published in the past years.</div>
<div style><br></div><div style>Best,</div><div style>Daniele</div><div sty=
le><br></div></div><div class=3D"gmail_extra"><br><br><div class=3D"gmail_q=
uote">On Mon, Apr 22, 2013 at 7:22 AM, Bernhard Wymann <span dir=3D"ltr">&l=
t;<a href=3D"mailto:[email protected]" target=3D"_blank">[email protected]<=
/a>&gt;</span> wrote:<br>
<blockquote class=3D"gmail_quote" style=3D"margin:0 0 0 .8ex;border-left:1p=
x #ccc solid;padding-left:1ex">Hi Walter<br>
<br>
Maybe you found it already, but I can give you some pointers:<br>
- <a href=3D"http://scr.geccocompetitions.com/previous-scr/" target=3D"_bla=
nk">http://scr.geccocompetitions.com/previous-scr/</a> (I think there is on=
e<br>
little &quot;paper&quot; available for each submitted opponent)<br>
- Google/ Google Scholar<br>
<a href=3D"http://scholar.google.com/scholar?q=3Dtorcs+car+reinforcement" t=
arget=3D"_blank">http://scholar.google.com/scholar?q=3Dtorcs+car+reinforcem=
ent</a><br>
- <a href=3D"http://groups.google.com/forum/#!forum/racingcompetition" targ=
et=3D"_blank">http://groups.google.com/forum/#!forum/racingcompetition</a><=
br>
- You can search as well torcs-users/devel with <a href=3D"http://sf.net" t=
arget=3D"_blank">sf.net</a><br>
<a href=3D"http://sourceforge.net/p/torcs/mailman/?source=3Dnavbar" target=
=3D"_blank">http://sourceforge.net/p/torcs/mailman/?source=3Dnavbar</a><br>
<br>
Not about learning, but about using TORCS:<br>
<a href=3D"http://www.youtube.com/playlist?list=3DPLq-L0hhLuRI23uh_HvNTnOD0=
7esKsZkrt" target=3D"_blank">http://www.youtube.com/playlist?list=3DPLq-L0h=
hLuRI23uh_HvNTnOD07esKsZkrt</a><br>
<br>
Other experiences and thoughts?<br>
<br>
Best regards<br>
<br>
Bernhard<br>
<div><div class=3D"h5"><br>
<br>
On 04/22/2013 05:37 AM, jlwalter wrote:<br>
&gt; Hello everyone,<br>
&gt;<br>
&gt; My name is Jeremiah and I&#39;m starting a research project on Reinfor=
cement<br>
&gt; Learning testing different algorithms&#39; effectiveness at &#39;learn=
ing to<br>
&gt; drive&#39;, or dealing with continuous actions. And I&#39;m going to u=
se TORCS<br>
&gt; as my simulation!<br>
&gt;<br>
&gt; So my question is, has anyone done any similar Reinforcement Learning<=
br>
&gt; research and have you any tips or recommendations when it comes to<br>
&gt; setting the simulation environment up?<br>
&gt; I appreciate any help I can get!<br>
&gt;<br>
&gt; Thankyou,<br>
&gt; Jeremiah Walter<br>
&gt; BComp, University of Tasmania<br>
&gt;<br>
&gt;<br>
</div></div>&gt; ----------------------------------------------------------=
--------------------<br>
&gt; Precog is a next-generation analytics platform capable of advanced<br>
&gt; analytics on semi-structured data. The platform includes APIs for buil=
ding<br>
&gt; apps and a phenomenal toolset for data science. Developers can use<br>
&gt; our toolset for easy data analysis &amp; visualization. Get a free acc=
ount!<br>
&gt; <a href=3D"http://www2.precog.com/precogplatform/slashdotnewsletter" t=
arget=3D"_blank">http://www2.precog.com/precogplatform/slashdotnewsletter</=
a><br>
&gt;<br>
&gt;<br>
&gt;<br>
&gt; _______________________________________________<br>
&gt; Torcs-devel mailing list<br>
&gt; <a href=3D"mailto:[email protected]">Torcs-devel@lists=
.sourceforge.net</a><br>
&gt; <a href=3D"https://lists.sourceforge.net/lists/listinfo/torcs-devel" t=
arget=3D"_blank">https://lists.sourceforge.net/lists/listinfo/torcs-devel</=
a><br>
&gt;<br>
<br>
<br>
---------------------------------------------------------------------------=
---<br>
Precog is a next-generation analytics platform capable of advanced<br>
analytics on semi-structured data. The platform includes APIs for building<=
br>
apps and a phenomenal toolset for data science. Developers can use<br>
our toolset for easy data analysis &amp; visualization. Get a free account!=
<br>
<a href=3D"http://www2.precog.com/precogplatform/slashdotnewsletter" target=
=3D"_blank">http://www2.precog.com/precogplatform/slashdotnewsletter</a><br=
>
_______________________________________________<br>
Torcs-devel mailing list<br>
<a href=3D"mailto:[email protected]">[email protected]=
ceforge.net</a><br>
<a href=3D"https://lists.sourceforge.net/lists/listinfo/torcs-devel" target=
=3D"_blank">https://lists.sourceforge.net/lists/listinfo/torcs-devel</a><br=
>
</blockquote></div><br></div>

--0015175cfe80a8dcf804daf419c4--


--===============5625410955837368765==
Content-Type: text/plain; charset="us-ascii"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
Content-Disposition: inline

------------------------------------------------------------------------------
Precog is a next-generation analytics platform capable of advanced
analytics on semi-structured data. The platform includes APIs for building
apps and a phenomenal toolset for data science. Developers can use
our toolset for easy data analysis & visualization. Get a free account!
http://www2.precog.com/precogplatform/slashdotnewsletter
--===============5625410955837368765==
Content-Type: text/plain; charset="us-ascii"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
Content-Disposition: inline

_______________________________________________
Torcs-devel mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/torcs-devel

--===============5625410955837368765==--