mutable struct Agent
learner::AbstractReinforcementLearner
policy::AbstractPolicy
callback::AbstractCallbackTabularReinforcementLearning.Agent — Method.Agent(learner; policy = EpsilonGreedyPolicy(.1), callback = NoCallback())TabularReinforcementLearning.Agent — Method.Agent(learner::NstepLearner; policy = EpsilonGreedyPolicy(.1), callback = NoCallback())Replaces policy with SoftmaxPolicy1 for baselearner of type AbstractPolicyGradient.
TabularReinforcementLearning.Agent — Method.Agent(learner::AbstractPolicyGradient; policy = SoftmaxPolicy1(), callback = NoCallback())mutable struct RLSetup
agent::Agent
environment
metric::AbstractEvaluationMetrics
stoppingcriterion::StoppingCriterionTabularReinforcementLearning.learn! — Method.learn!(learner, policy, callback, environment, metric, stoppingcriterion)TabularReinforcementLearning.learn! — Method.learn!(agent::Agent, environment, metric, stoppingcriterion)TabularReinforcementLearning.learn! — Method.learn!(x::RLSetup)TabularReinforcementLearning.run! — Function.run!(learner, policy, callback, environment, metric, stoppingcriterion)TabularReinforcementLearning.run! — Method.run!(agent::Agent, environment, metric, stoppingcriterion)TabularReinforcementLearning.run! — Method.run!(x::RLSetup)