How can I ensure convergence of DDQN, if the true Q-values for different actions in the same state are very close?
Is a calculus or ML approach to varying learning rate as a function of loss and epoch been investigated?
How to create and train (with mutation and selection) a neural network to predict the next state of a board?
Why does reinforcement learning using a non-linear function approximator diverge when using strongly correlated data as input?
Only top scored, non community-wiki answers of a minimum length are eligible