arXiv Machine Learning August 4, 2026 By Patrick Helm, Jan-Niklas Doerr, Joren Gijsbrechts, Stefan Minner

Hard Constraints, Smooth Gradients: Learning Feasible Inventory Policies via Differentiable Projection

Read the original on arXiv Machine Learning →

arXiv:2608. 02343v1 Announce Type: cross Abstract: Many operational problems are constrained sequential decision processes with large, combinatorial action spaces and interdependent feasibility constraints.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv AI

Jun 6

Learning to replenish: A hybrid deep reinforcement learning for dynamic inventory management in the pharmaceutical supply chains

arXiv:2606. 06201v1 Announce Type: new Abstract: Pharmaceutical supply chains (PSCs) struggle with inventory management (IM) due to unpredictable demand patterns and variable lead times associated with restocking.

By Amandeep Kaur, Gyan Prakash

reinforcement-learning benchmarks

arXiv Machine Learning

Jun 15

Optimal Hidden-Target Learning for Online Inventory Optimization on General Convex Sets

arXiv:2606. 14679v1 Announce Type: new Abstract: Online inventory optimization (OIO) is online convex optimization with physical memory: inventory carryover makes the feasible action set depend on the past.

By Anthony Pineci, Yunzong Xu

safety

arXiv Machine Learning

Jun 25

Bias-Controlled Primal-Dual Natural Actor-Critic: Optimal Rates for Constrained Multi-Objective Average-Reward RL

arXiv:2606. 25012v1 Announce Type: new Abstract: Many reinforcement learning (RL) problems in the infinite-horizon average-reward setting require optimizing multiple conflicting objectives while satisfying multiple safety constraints.

By Ankur Naskar, Swetha Ganesh, Vaneet Aggarwal

agents reinforcement-learning safety

arXiv AI

Jun 17

Online LLM Selection via Constrained Bandits with Time-Varying Demand

arXiv:2606. 17489v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly deployed in edge-cloud inference systems to handle diverse user tasks with heterogeneous accuracy, latency, and cost profiles.

By Yin Huang, Qingsong Liu, Jie Xu

llms reinforcement-learning benchmarks

arXiv AI

Jun 2

Position Paper: Post-Solve Robustness in Decision Engines: Feasible Regions and Smoothness Under Perturbations

arXiv:2606. 00002v1 Announce Type: new Abstract: Mixed-Integer Linear Programming (MILP) decision engines routinely output nominally optimal plans for high-stakes industrial systems.

By Yi-Xiang Hu

safety

arXiv Machine Learning

Jun 9

Reformulate LLM Reinforcement Learning for Efficient Training under Black-box Discrepancy

arXiv:2606. 08779v1 Announce Type: new Abstract: Reinforcement Learning (RL) has emerged as a pivotal post-training paradigm, yet it frequently suffers from unpredictable sub-optimum performance or even training collapses.

By Jiashun Liu, Runze Liu, Xu Wan, Jing Liang, Hongyao Tang, Ling Pan

llms reinforcement-learning

Related stories

Learning to replenish: A hybrid deep reinforcement learning for dynamic inventory management in the pharmaceutical supply chains

Optimal Hidden-Target Learning for Online Inventory Optimization on General Convex Sets

Bias-Controlled Primal-Dual Natural Actor-Critic: Optimal Rates for Constrained Multi-Objective Average-Reward RL

Online LLM Selection via Constrained Bandits with Time-Varying Demand

Position Paper: Post-Solve Robustness in Decision Engines: Feasible Regions and Smoothness Under Perturbations

Reformulate LLM Reinforcement Learning for Efficient Training under Black-box Discrepancy