SpaceInvader story continues

I have been so busy writing my book on Julia that I could not dedicate time to finalizing Space Invaders.

Previously I have managed to train the model to reach 200, but after implementing a few changes, it dropped back to random policy and stalled on around 165.

I have worked on a number of changes to the environment and model:

  1. I have implemented 3-channel model, where each channel corresponds to a frame.
  2. I have used DQN definition from NIPS 2013.
  3. I have tried shrinking the frame size and taking every second pixel both on x and y-axis, but it did not work well. The current implementation is taking every second pixel on the y-axis and every pixel from the x-axis.
  4. I have tried retraining the model after every frame and mixing it the frames from the past. I have changed the implementation, and my update interval is 5, which means I am updating my model on every fifth frame.
  5. I am clipping the predictions to be over 0.
  6. I am also considering every reward I am getting to be either 0 or 1.

My model is in training. It has been 4500 episodes, and I am over 200 in reward. Will be training it longer to see if that works.

Will be check-ing the code shortly!

SpaceInvader story continues

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s