Evaluation Metrics
struct AllRewards <: AbstractEvaluationMetrics
rewards::Array{Float64, 1}
Records all rewards.
TabularReinforcementLearning.AllRewards
— Method.AllRewards()
Initializes with empty array.
EvaluationPerEpisode <: AbstractEvaluationMetrics
values::Array{Float64, 1}
metric::SimpleEvaluationMetric
Stores the value of the simple metric
for each episode in values
.
EvaluationPerEpisode(metric = MeanReward())
Initializes with empty values
array and simple metric
(default MeanReward
). Other options are TimeSteps
(to measure the lengths of episodes) or TotalReward
.
EvaluationPerT <: AbstractEvaluationMetrics
T::Int64
counter::Int64
values::Array{Float64, 1}
metric::SimpleEvaluationMetric
Stores the value of the simple metric
after every T
steps in values
.
EvaluationPerT(T, metric = MeanReward())
Initializes with T
, counter
= 0, empty values
array and simple metric
(default MeanReward
). Another option is TotalReward
.
mutable struct MeanReward <: TabularReinforcementLearning.SimpleEvaluationMetric
meanreward::Float64
counter::Int64
Computes iteratively the mean reward.
TabularReinforcementLearning.MeanReward
— Method.MeanReward()
Initializes counter
and meanreward
to 0.
struct RecordAll <: AbstractEvaluationMetrics
r::Array{Float64, 1}
a::Array{Int64, 1}
s::Array{Int64, 1}
isterminal::Array{Bool, 1}
Records everything.
TabularReinforcementLearning.RecordAll
— Method.RecordAll()
Initializes with empty arrays.
mutable struct TimeSteps <: SimpleEvaluationMetric
counter::Int64
Counts the number of timesteps the simulation is running.
TabularReinforcementLearning.TimeSteps
— Method.TimeSteps()
Initializes counter
to 0.
mutable struct TotalReward <: TabularReinforcementLearning.SimpleEvaluationMetric
reward::Float64
Accumulates all rewards.
TabularReinforcementLearning.TotalReward
— Method.TotalReward()
Initializes reward
to 0.