2 papers
cs.AI2026
Hard Constraints, Smooth Gradients: Learning Feasible Inventory Policies via Differentiable Projection
Patrick Helm, Jan-Niklas Doerr, Joren Gijsbrechts +1
Many operational problems are constrained sequential decision processes with large, combinatorial action spaces and interdependent feasibility constraints. Mixed-integer linear pro…
cs.AI2025
Speeding up Policy Simulation in Supply Chain RL
Vivek Farias, Joren Gijsbrechts, Aryan Khojandi +2
Simulating a single trajectory of a dynamical system under some state-dependent policy is a core bottleneck in policy optimization (PO) algorithms. The many inherently serial polic…