# Addressing Terminal Constraints in Data-Driven Demand Response Scheduling

arXiv: https://arxiv.org/abs/2605.14741 · HTML: https://mlsanity.com/paper/2605.14741/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in RL for energy, networks and operations, one of 15 directions in Deep reinforcement learning methods.
- Builds on 7 of its 18 references that are in the map.
- First posted on arXiv 14 May 2026.

## Placed in

- Deep reinforcement learning methods / [RL for energy, networks and operations](https://mlsanity.com/deeprl/rl-for-energy-networks-and-operations/)

## Builds on (most cited first, 7 of 7)

- [Deep Reinforcement Learning with Shallow Controllers: An Experimental Application to PID Tuning](https://mlsanity.com/paper/2111.07171/) (2021)
- [Chance Constrained Policy Optimization for Process Control and Optimization](https://mlsanity.com/paper/2008.00030/) (2020)
- [Goal-Space Planning with Subgoal Models](https://mlsanity.com/paper/2206.02902/) (2022)
- [Constrained Model-Free Reinforcement Learning for Process Optimization](https://mlsanity.com/paper/2011.07925/) (2020)
- [Data-Driven Model Reduction and Nonlinear Model Predictive Control of an Air Separation Unit by Applied Koopman Theory](https://mlsanity.com/paper/2309.05386/) (2023)
- [Hierarchical RL-MPC for Demand Response Scheduling](https://mlsanity.com/paper/2502.13714/) (2025)
- [Survey and Tutorial of Reinforcement Learning Methods in Process Systems Engineering](https://mlsanity.com/paper/2510.24272/) (2025)

## Abstract (arXiv)

Electrified chemical processes are incentivized by exposure to time-varying electricity markets to operate flexibly, but participating in demand response schemes can require satisfying terminal constraints over long horizons. Specifically, terminal constraints may be required when computing optimal schedules in order to preserve dynamic stability. Model-based optimization methods are computationally costly, and data-driven scheduling via reinforcement learning (RL) faces severe credit-assignment challenges. We integrate Goal-Space Planning (GSP) with Deep Deterministic Policy Gradient (DDPG), using learned temporally abstract models over discrete subgoals to propagate value across extended horizons. Using a simulated air separation benchmark, we demonstrate the proposed approach improves sample efficiency over standard DDPG while satisfying terminal storage constraints, mitigating myopic control behavior.