Learning
mutable struct Agent
    learner::AbstractReinforcementLearner
    policy::AbstractPolicy
    callback::AbstractCallback
source
Agent(learner; policy = EpsilonGreedyPolicy(.1),  callback = NoCallback())
source
Agent(learner::NstepLearner; policy = EpsilonGreedyPolicy(.1), callback = NoCallback())

Replaces policy with SoftmaxPolicy1 for baselearner of type AbstractPolicyGradient.

source
Agent(learner::AbstractPolicyGradient; policy = SoftmaxPolicy1(), callback = NoCallback())
source
mutable struct RLSetup
    agent::Agent
    environment
    metric::AbstractEvaluationMetrics
    stoppingcriterion::StoppingCriterion
source
learn!(learner, policy, callback, environment, metric, stoppingcriterion)
source
learn!(agent::Agent, environment, metric, stoppingcriterion)
source
learn!(x::RLSetup)
source
run!(learner, policy, callback, environment, metric, stoppingcriterion)
source
run!(agent::Agent, environment, metric, stoppingcriterion)
source
run!(x::RLSetup)
source