in terms of motion planning, what are the difference between gradient-based motion planning (for instance, CHOMP http://www.nathanratliff.com/thesis-research/chomp) and deep reinforcement learning?

Both of the approaches are iterated many times to optimize the given gradient function/ reward function in the simulation. Can someone give his/her insights into these two methods?



Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.