Guiding Agent Games

So, we've covered most of the basics of the current models of Agent Games. Now, why are they interesting?

These agent react to the last few 0s and 1s in a sequence of 0s and 1s, and then create a response. This response is then the next 0 or 1 in the sequence, and the agents drop the oldest digit and use the new sequence. All this is great, but...

You can feed in your own 0s and 1s to 'get them ready' up to the current time. And then, you can force the agents to follow every possible combination of 0s and 1s as far into the future as you want.

You can force them to play just like some other game, like currency market returns, and then see how the agents react. In the future.

Risk managment and trading might have a use for peering into the future of a market. Risk managment might even have a use for knowing that a model doesn't have a solid prediction.