Model Based Planning
Today I covered lecture 8 in Berkeley’s deep rl course. This covered model based planning, which optimizes a policy when the model is given.
This was a lot of ORIE stuff, which is relatively foreign to me. For example, unlike previous lectures which still had the applicable neural network, this chapter covered mathematical optimization methods which I’m still unfamiliar with. However, I have been looking into the mathematical programming courses offered by the ORIE graduate program, but at the current moment I don’t think this is that applicable to me. However, I expect the next chapter, which covers model based reinforcement learning, to be more applicable to my current state.
Below are my notes