Predict.Neural.Network: Evaluate Neural Network

In MartinKies/USLR: Reinforcement Learning with R

Description

Evaluate a model based on a game.state

Usage

Predict.Neural.Network(model, model.par, state, action = NULL)

Arguments

model	A trained Neural Network e.g. given by Setup.Neural.Network.
state	A game.state after being encoded by the game.object.
action	Only the relevant action is displayed

MartinKies/USLR documentation built on Nov. 10, 2019, 5:24 a.m.