BACKGROUD:
The
proposed simulator server and related documentation can be downloaded here.
FIRST
TASK: A single robot learns the skill shootGoal
LEARNING TASK: The
agent learns this skill with all levels of the keeper (e.g. static, random,
blockBall, interceptBall ).
PARAMETERS:
|
Input |
DistToGoal,
DistToKeeper, AngleToGoal, AngleToKeeper |
|
Output |
transVel,
rotVel, kickBall |
|
Success |
Goal |
|
Failure |
ballLost
(not in Goal) |
SECOND
TASK: A single robot learns to support an offender.
LEARNING TASK: The
scenario could be learned by randomly placing the offender with ball and the supporter
(the learning robot) in front of the goal. The supporting robot has to reach a
position and orientation, which allows the offender to shoot a goal indirectly
via the supporting robot. The offender will automatically shoot if receiving
the "commSignalReady" from the supporter. If the reflecting ball hits
the goal, the supporter will be rewarded.
PARAMETERS:
|
Input |
AngleToGoal, DistToGoal, AngleToKeeper, DistToKeeper,
AngleToOffender |
|
Output |
commSignalReady |
|
Success |
Goal |
|
Failure |
ballLost
(not in Goal and not at offender) |
THIRD TASK: The
offender selects from one of the learned skills (not necessarily within
hierarchical RL)
LEARNIG TASK: The offender has the possibilities to either shoot directly or to turn towards the supporter until receiving the commSignalReady. The scenario could be learned by randomly plaicing a static goalkeeper into the goal.
PARAMETERS:
|
Input |
DistToGoal, DistToKeeper, AngleToGoal, AngleToKeeper, DistToSupporter,
commSignalReady |
|
Output |
transVel, rotVel, kickBall |
|
Success |
Goal |
|
Failure |
ballLost
and not in Goal |
^ TOP
BACKGROUD:
In this benchmark task, there was a need
for some pre-implemented agents. We developed some simple agents for
that reason and are now ready for
download.
Random fire brigade:
http://ce.sharif.edu/~arian/learn-sig/Firebrigade-1.tar.gz
Fire brigade with simple targeting algorithm:
http://ce.sharif.edu/~arian/learn-sig/FireBrigade-2.tar.gz
(This fire brigade targeting algorithms is
based on
1- Distance of the agent to the building
2- Building's fireyness
3- Number of on fire buildings near that
building)
Police forces:
http://ce.sharif.edu/~arian/learn-sig/police-sig.tar.gz
SCENARIO:
The 1/100 of Kobe city map is used.
The test will run on a single initial configuration
(i.e. same Shindopoly, Galpoly and gisini).
There is no civilian and no ambulance in
the city and there are only five police forces and five fire brigades.
LEARNING
TASK:
The aim of the agents is just to
extinguish fires.
Since the main challenge in this task is
learning to coordinate, the agents shouldn't use a coordination protocol.
You have control of just 'n' out of
5 fire brigades and 'm' out of 5 police forces.
There are different initial situations:
·
n = 2 and m
= 2
I
- Other 2 fire brigades extinguish their nearest fiery building
and police forces move
randomly.
II - Other 2
fire brigades uses a specific targeting algorithm
for selecting fiery buildings
and police forces move randomly.
III - Other 2
fire brigades and 2 police forces use a specific
learning algorithm
IV - Other 2
fire brigades and police forces behavior is one of
the known behaviors. The
agents are given a total simulation
to learn their teammates behavior
and the second run counts.
·
n = 5 and m
= 5
(the
order is from easier to harder)
^
TOP