Dear All,
There are some points that i think should be mentioned:
First, I think there should be attached change logs to every release of
rescue kernel or anyhow anounce the changes with any release, as
Mr.Saboorian has pointed it before.
Second I think the first time i realized the rounding of hp and damage was
about 2 month and a half ago, when Mr.Sabourian has mentioned it in reply to
Ms.Mosaffazade: http://r-resc.a-eskwadraat.nl/archive/2006/02/1451.html
At last, Although i agree with the fact that this kind of rounding will
cause a shock in every ambulance developement team, but it is completely
reasonable to have such noise in the agent's perception of a civilian, not
only because it is more realistic but also it will restrain the act of
reverse engineering -i do not point to any specific team-.
Anyway i think there is no need to apply another estimation method to handle
this noise, there are some specific methods for handling noise of data,
therefore I think there should be a noise handler layer before the previous
used estimation layer of every team.
Regards,
On 5/9/06, Utku Tatlędede <utkutatlidede@gmail.com> wrote:
>
> Dear All,
> In the previous years competition Impossibles team have implemented a
> method to increase the accuracy of the civilian lifetime estimation. If you
> watch any logs from the previous year I am sure that you can realize the
> method as their signature.
> Now
> 1- I don't agree nor disagree with any comments. I dont know the things in
> detail. I just want to emphasize that a good estimator is one thing a good
> exploration strategy is another thing.
> 2- I dont say other teams didnt implement such methods I just remember
> Impossibles was using a strategy which our team did not implemented. May be
> other teams also implemented such strategies but I was interested in
> Impossibles because of their success.
> 3- I remember an email about the change very long ago but I could have
> time to retrain my algorithm however I believe that it will handle the case
> since it will say hurryup to my agents. I think the only problem is
> receiving 0 for hp under 500 which the civilian is alive but the agents may
> sense it as dead...
> 4- I think the problem is not change of sense, the new comuniction
> protocoll. I had to reimplement the tools/viewers we before and try to run
> kernel at start and lost almost two month (I tried to port the code base to
> rescuecore inthe mean time) upto the kernel 0.49.3 is released. Now I
> develop on 0.48 and it will be a big surprise for me to run the agents on
> the new version. I cant use 0.49.5 because the civilian simulator uses to
> much CPU on my machine...
>
> Best regards...
>
>
>
> On 5/9/06, a_fathi@ce.sharif.edu < a_fathi@ce.sharif.edu> wrote:
> >
> > Dear Friends,
> >
> > Firstly I guess both Babak and Arash are assuming we did reverse
> > engineering to write our AmbulanceTeam agents in Impossibles. I'm here
> > to
> > inform anyone thinking like this, that our estimation routine was
> > extracted from some gauges and logs on different civilians in different
> > runs. We never even read the source code of MiscSimulator but every one
> > else working in other teams like Caspian and S.O.S had completely read
> > the
> > source code. We can completely describe our method for every one
> > interested. Something more enthusiastic is we can compare different
> > estimations in different teams. Currently I am working with Mr.
> > Tavakkoli
> > in Poseidon who was one of the implementors of S.O.S's AmbulanceTeams
> > and
> > he thinks their estimation is better than Imposssible's. But what made
> > Impossibles to be Impossibles was the algorithm AmbualnceAgents were
> > using
> > to implement coalition in different situations.
> > Also we can explain this algorithm for you too if you want. I think what
> > you do is a kind of dispute without confidence about what really
> > happened.
> >
> > I completely agree with Babak in the definition of RoboCup. The
> > solutions
> > should be MultiAgent and AI solutions. Assume a team is using
> > Reinforcement Learning for estimating the death time of a civilian. We
> > think it needs 5,000 runs, each run at least 300 seconds. we think it
> > will
> > take a month to have a estimation with 90% precision for the death time
> > of
> > civilians. Now if you are going to change the HP and Damage just a month
> > before competitions guess what will happpen. Yes it is 4 months that the
> >
> > change is happened. As we do not read the source code of the kernel we
> > didn't know it has chnged but as you do you knew. Mr Saboorian announced
> > it just two weeks ago.
> >
> > Me, Mr Tavakkoli, Ms Mostafazadeh and my friends in Impossibles think
> > the
> > strategy AmbulanceTeams are using currently needs to completely change.
> > Yes Arash, estimation function won't change many but you have no
> > accurate
> > estimation anymore. Then you should change your priority parameters for
> > civilians and every thing will completely change. The current algorithm
> > is
> > emphesizing on the acurate estimation but without it is nothing.
> >
> >
> >
> > Sincerely Yours,
> > Alireza Fathi.
> > Team Leader of Poseidon Rescue simulation Team,
> > Previous Team Member of Impossibles.
> >
> >
> >
> >
> >
> > On Tue, May 9, 2006 4:38 pm, Babak BehSaz wrote:
> > > Dear Alireza,
> > >
> > >
> > > I have two comments about your complaint.
> > > First, I agree that technical committee should release
> > > the final package sooner than this (sooner than release time of
> > package
> > > 0.49a). I think technical
> > > committee should try to solve this problem for next years. I think it
> > will
> > > promote quality of competitions dramatically. But, I think Arash's
> > argument
> > > is logical, why don't you complained when package 0.49a was released?
> > This
> > > change was announced four months ago and now, I think complaining is
> > not
> > > acceptable. Second, let's look what is RoboCup! According to
> > > explanation of Recoup official site, "RoboCup is an international
> > joint
> > > project to promote AI, robotics, and related field. It is an attempt
> > to
> > > foster AI and intelligent robotics research by providing a standard
> > problem
> > > where wide range of technologies can be integrated and examined".
> > > Therefore, we technically
> > > expect that team's efforts promote AI. Thus, technical committee can
> > assume
> > > teams designed their agent according to the concepts and methods of
> > AI.
> > > With this assumption, recent changes made by technical
> > > committee doesn't have any problems (and in my opinion, they should
> > try to
> > > apply such changes in entire package more and more). They just changed
> > the
> > > precision of data that will be received by agents, not even model of
> > > generation of these data. Hence, it is obvious that if your team uses
> > an
> > > AI method, you will
> > > not confront any problems. Otherwise, it is your problem that you are
> > not
> > > selected a method consistent with the definition of RoboCup. Look at
> > most
> > > of current teams' methods, THESE METHODS IS DISASTROUS, not recent
> > > changes. I regret to see that our league made a very few contributions
> > to
> > > promotion of AI, of course if made any (our teams are only using
> > simple
> > > methods to obtain better results without even trying to use a more
> > > scientific approach!).
> > >
> > > Best Regards,
> > > Babak Behsaz
> > > Previous S.O.S. Member
> > >
> > >
> > >
> > > __________________________________________________
> > > Do You Yahoo!?
> > > Tired of spam? Yahoo! Mail has the best spam protection around
> > > http://mail.yahoo.com
> > > _______________________________________________
> > > robocup-rescue-s mailing list robocup-rescue-s@mailman.cc.gatech.edu
> > > https://mailman.cc.gatech.edu/mailman/listinfo/robocup-rescue-s
> > >
> > >
> >
> >
> > _______________________________________________
> > robocup-rescue-s mailing list
> > robocup-rescue-s@mailman.cc.gatech.edu
> > https://mailman.cc.gatech.edu/mailman/listinfo/robocup-rescue-s
> >
>
>
> _______________________________________________
> robocup-rescue-s mailing list
> robocup-rescue-s@mailman.cc.gatech.edu
> https://mailman.cc.gatech.edu/mailman/listinfo/robocup-rescue-s
>
>
>
-- Hossein Azizpour, Member of S.O.S team, Robocup Researches Center, Amirkabir University of Technology, -- Hossein Azizpour, Member of S.O.S team, Robocup Researches Center, Amirkabir University of Technology,
_______________________________________________
robocup-rescue-s mailing list
robocup-rescue-s@mailman.cc.gatech.edu
https://mailman.cc.gatech.edu/mailman/listinfo/robocup-rescue-s
Received on Wed May 10 14:32:25 2006
This archive was generated by hypermail 2.1.8 : Wed 10 May 2006 - 12:32:26 GMT