Proximal Residual Value Functions for Consistent Planning and Real-Time Execution
We study two-timescale decision systems in which a planning layer periodically supplies a continuation-value function to a real-time optimizer that allocates arriving resources, with inventory placement as our motivating application. We propose an end-to-end reinforcement learning (RL) method for learning this function...
Harrison Waldon, Carson Eisenach, Akhil Bagaria et al.
· 0 citations