Path Learning with Trajectory Advantage Regression

We are concerned with the problem of path learning (PL) in an offline fashion. The goal of PL is to find the path ψ maximizing the yield J (ψ), whereas the feasible set of paths Ψ and the shape of the yield function J: Ψ R are both (partially or entirely) unknown, hence to be estimated from fixed observational data collected in advance (i.e., the offline setting). To address this problem, we propose to frame the offline PL problem as a special sub-problem of the offline reinforcement learning (RL) and derived a novel algorithm to solve it. This algorithm allows us to find the optimal path in Ψ efficiently and also gives a new path-scoring method useful for explaining the (sub-) optimality of paths in terms of the path elements. The rest of the paper is organized as follows. We start with introducing preliminary facts and formulations in Section 2. Then, we show the reducibility of PL to RL in Section 3, which is the key to our method presented in Section 4. Finally, we conclude the paper discussion the related work in Section 5 and summarizing the findings and future directions in Section 6.