Open 360disrupt opened 5 years ago
It is not a problem, it is just that I started developing it but I had not enough time to fully test and finish it. Some things were working but actually need to be revamped etc . So for now the feature is not functional.
On the MIT lecture e.g. they have an example of a DQN with convolutional layers. https://youtu.be/i6Mi2_QM3rA?t=1531 Or here: https://towardsdatascience.com/welcome-to-deep-reinforcement-learning-part-1-dqn-c3cab4d41b6b
Would be interested if this is a problem in general or just with this implementation of DQN. I couldn't find anywhere that it is a problem.