wkwan / ScrimBrain

Reinforcement Learning in Fortnite With Real-Time Screen Capture and Windows Input Simulation
37 stars 4 forks source link

Initialize Weights from Computer Vision Model #2

Open wkwan opened 2 months ago

wkwan commented 2 months ago

train_model.py doesn't specify any weight initialization (not sure what SB3 does by default, is it random?).

Hypothesis If we can initialize the weights with some layers from a pretrained computer vision model, this might speed up training and/or avoid early local convergence. Specifically, the convolutional layers seem most useful for feature extraction.

Task Write a new version of train_model.py that initializes new models with weights from the convolutional layers of a computer vision model like Resnet 50.

Challenges This probably requires implementing a custom policy, which requires understanding some of the internals of the training algorithm. From previous experiments, we know that DQN works on the current environment so the ideal first experiment for this task is to write a custom policy for DQN. But it might be easier to write a custom policy for another training algorithm.