Stopping Criteria
mutable struct ConstantNumberEpisodes <: StoppingCriterion
N::Int64
counter::Int64
Stops learning when the agent has finished 'N' episodes.
ConstantNumbeEpisodes(N) = ConstantNumberEpisodes(N, 0)
mutable struct ConstantNumberSteps <: StoppingCriterion
T::Int64
counter::Int64
Stops learning when the agent has taken 'T' actions.
ConstantNumberSteps(T) = ConstantNumberSteps(T, 0)