Description Usage Arguments Details
View source: R/PrisonersDilemmaStratTourn.R
Each strategy within the game.object plays against itself one time
1 | Memory.Self.Play.PD(game.object, algo.par)
|
game.object |
as specified by Get.Game.Object |
algo.par |
as e.g. given by Get.Def.Par.QLearning |
Outputs List of lists with the following elements:
state - Already encoded game state.
action - Which of the actions has been taken? This is a single action if algo.par implies classical state-action pairs and the complete action row up to this point if a time.series approach is used (currently only use.rnn)
next.state - resulting next, encoded, state
reward - What did we get from transitioning to the next state?
done - Boolean; is the game over?
Public Function which might be called by algorithms.
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.