mlsanityData to 14 Oct 2026

Bridging the Sim-to-Real Gap in Reinforcement Learning-Based Industrial Dispatching through Execution Semantics

arXiv 2605.29078 ↗First posted 27 May 2026cs.AI cs.LGcited by 0

On the map: Deep reinforcement learning methods → RL for energy, networks and operations

Abstract (arXiv)

Event-driven scheduling policies are increasingly deployed in industrial environments, where decisions are made under asynchronous and partially observed system states. As a result, decision states are not temporally consistent, action admissibility is not explicitly defined, and the origin of execution errors remains ambiguous. These issues limit both reliability and interpretability. To address this gap, a policy-neutral execution and measurement layer is proposed to mediate between scheduling policies and the industrial execution environment. The layer constructs decision-valid snapshots from asynchronous event streams, defines a standardized execution contract with explicit action admissibility, and records outcomes as divergences between policy intent, transactional outcomes, physical execution, and human intervention. This enables a separation between decision semantics and execution behavior and makes deployment mismatch observable and structurally attributable. The proposed framework is evaluated using a discrete-event simulation. The results show analytical benefits across all observation lag regimes, as undifferentiated execution failures are transformed into structured, typed outcomes with full attribution coverage. Operational benefits are strongest under low observation lag, where avoidable execution errors can be prevented before commitment. Overall, the layer turns execution uncertainty into supervisory data for evaluation and policy refinement.

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 27 May 2026.

Builds on

7 of 18 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025A Production Scheduling Framework for Reinforcement Learning Under Real-World Constraints16 Jun

Other references · 6

  1. 2020Sim-to-Real Transfer in Deep Reinforcement Learning for Robotics: a Surveycited by 413
  2. 2019Challenges of Real-World Reinforcement Learningcited by 291
  3. 2019Action Robust Reinforcement Learning and Applications in Continuous Controlcited by 174
  4. 2024Graph Neural Networks for Job Shop Scheduling Problems: A Surveycited by 15
  5. 2024Offline Reinforcement Learning for Learning to Dispatch for Job Shop Schedulingcited by 6
  6. 2026Scalable Production Scheduling: Linear Complexity via Unified Homogeneous Graphscited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Harmonizing Real-Time Constraints and Long-Horizon Reasoning: An Asynchronous Agentic Framework for Dynamic Scheduling
  2. 2025Adaptive Reinforcement Learning for State Avoidance in Discrete Event Systems
  3. 2026Event-Driven Reinforcement Learning Enables Long-Horizon Control in Semiconductor Fabrication
  4. 2024Demystifying Reinforcement Learning in Production Scheduling via Explainable AI
  5. 2026The Challenges of Using Reinforcement Learning for Controlling Industrial Energy Systems
  6. 2026A Policy-Driven Runtime Layer for Agentic LLM Serving
  7. 2026Policy-Based Reinforcement Learning with Action Masking for Dynamic Job Shop Scheduling under Uncertainty: Handling Random Arrivals and Machine Failures
  8. 2025Scalability of Reinforcement Learning Methods for Dispatching in Semiconductor Frontend Fabs: A Comparison of Open-Source Models with Real Industry Datasets