Putting aside things applicable to neural networks such as dropout, l2 regularization, new opitmizers - what are the cool things I should be adding to my Reinforcement Learning algorithm (Q-Learning and SARSA) to make it stronger, in 2018?
So far, I know these:
- Experience Replay (gather experiences, then train at once on some of them)
- Slowly making our network approach the Q-values of a Target Network. The target Network is only cloned sometimes.
- If our function approximator is RNN and our Memory Bank stores sequences of several timesteps, after selecting few random sequences from Memory bank, only backpropagate a half of the sequence, without going back to its start