Advantage.function: Calculates N-Step Returns or weighted Temporal Difference...
In MartinKies/USLR: Reinforcement Learning with R

Internal function called from Worker.A3C

1 2	Advantage.function(state, model, model.par, algo.par, game.object, queue, done)

`state`	Actual game state as returned by `State.Transition.<NAME>`.
`model`	A model as given by `Setup.Neural.Network.A3C` or `Setup.Neural.Network.A3C.LSTM`.
`model.par`	A list as given by `Get.Def.Par.Neural.Network.A3C` or `Get.Def.Par.Neural.Network.A3C.LSTM`.
`algo.par`	A list as given by `Get.Def.Par.A3C`.
`game.object`	A Game Object (list) as defined by `Get.Game.Object.<NAME>`.
`queue`	Game history of the last n rounds given by `Convert.2.train`.
`done`	Boolean specifiying wether actual episode is ended. Determines if a Bootstrap Value has to be calculated.