Search code examples
pythontensorflowkeraslstmrecurrent-neural-network

Limit RNN legal output for each time step

I'm trying to make an RNN predict moves for a card game. In each time step, only certain actions are legal (i.e. some moves cannot be made in certain situations).

So at any given point through the game, one out of 12 moves is the correct one. Each move is labeled as an int in range 0 through 11. In most situations, only a subset of these are actually legal moves. So say I try to train the model, and it predicts e.g. move 4 in a situation, however only moves 2, 3 and 9 are legal at this time. After this move has been made, a different subset is allowed for the next time step. How do I make it predict from only a subset of the moves?

I haven't come so far as to coding the model yet, but I intend to use Keras/TensorFlow LSTM in Python to do this.

I would be happy if you could point me in a good direction here!

Solution

  • You can add a mask as an argument of calling your model.

    But the simpliest way is to get prediction as probabilities of all moves and then just ignore those which are not permitted.