Using Ocean Suite/ Dwave to enhance planning algorithms such as best first search, Astar, or Monte Carlo Tree Search?

Hi, I seen tutorials for the Ocean Suite to solve TSP, but if your problem isn't about hitting every state like TSP, but instead, you want to find a goal state, such as AI that play games or self driving cars. 

I can do a planning algorithm or reinforcement learning, but am interested if the TSP method can help improve performance over classical computers in planning/RL. Are there any example code where i can do that?

The Ocean Suite works well if the problem is exactly TSP, but what if the problem is slightly different, in this instance, we don't need to visit every state, just need to find the goal or high reward state