You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
This is an idea transferred from the previous IDEAS.md (#39 ):
Named Variables
It might also be more clear what is going on if we declared variables with names as shown in the example below.
This would be tougher to compile though, and it's not clear what the easiest way to express distributions or reward would be.
Ideas welcome!
mdp =@MDPbegin
xmax =10
ymax =10@statesbegin
x in1:10
y in1:10end@actionsbegin
dir in [:up, :down, :left, :right]
end@reward rdict =Dict(
#XXX no idea how to define this in terms of x and y
)
default_reward =0.0@transition#XXX what is the most concise way to define the transition distribution??
terminal =vals(reward)
discount =0.95
initial
end
The text was updated successfully, but these errors were encountered:
This is an idea transferred from the previous IDEAS.md (#39 ):
Named Variables
It might also be more clear what is going on if we declared variables with names as shown in the example below.
This would be tougher to compile though, and it's not clear what the easiest way to express distributions or reward would be.
Ideas welcome!
The text was updated successfully, but these errors were encountered: