Closed EXJUSTICE closed 3 years ago
Managed to solve this by introducing an array into the preprocessFrame wrapper into itself for evaluation purposes! But an official approach would be welcome!
Check out lecture #39. I show how to save video of the agent playing the game, and it renders with the original frames (not our grayscale / downsized images).
Thank you Phil,
You'll find my adaptation for your code for Doom here https://github.com/EXJUSTICE/Doom_DQN_GC/tree/master/PytorchDQN
Will you be doing a course on policy gradient models? Or is the Actor Critic course sufficient to cover the area in your opinion?
Also, I notice that that in DDQN, you specify that we must calculate S (t+1) through the eval and target networks, in this case S (t+1) is a state action value, correct? , as you do end up calling T.argmax() on it later.
Hi Phil,
Thank you for your course, I found it to be the most informative and clear approach to Pytorch OpenAI RL. I would like to view the results of the trained agent in action,
I've been previously using an array to store individual observation and and then using sk-video (See below) to make an .mp4 file out of it, or using the Monitor class.
However, as you've essentially wrapped up the environment itself, these approaches are no longer possible,as the agent expects the fully stacked, resized inputs of shape (1,84,84,4). I think it would be very helpful to get a simple way of viewing the performance of the trained agent in action as a supplementary as part of the course, is this possible?