In my problem, the agent does not follow the successive order of states, but selects with $\epsilon$ -greedy the best pair (state, action) from a priority queue. More specifically, when my agent goes to a state $s$ and opens its available actions $\{ a_i \}$ , then it estimates each $(s,a)$ pair (regression with DQN) and stores it into the queue. In order for my agent to change to state $s'$ , it picks the best pair from the queue instead of...
Originally asked by ddaedalus on Stack Exchange (ai) (CC BY-SA 4.0).
