Planning or Learning: Reliability and Cost in Multi-Asset Maintenance

A study posted to arXiv (2609.13566v1) empirically compared planning and reinforcement learning for multi-asset bearing maintenance using run-to-failure data, finding that planning enforces reliability as a hard constraint and yields zero-failure policies whose total cost is largely insensitive to failure-penalty magnitude, while RL agents optimize expected cost and accept occasional failures as penalties vary. The authors report RL achieves lower costs under low-penalty regimes but shows persistent non-zero failures even when penalties are high, and that lightweight constraint mechanisms such as reward shaping and action masking can encourage RL reliability. The study concludes planning suits strict-reliability, short-horizon deployments while RL suits cost-efficient policies where limited failures are acceptable, and offers its controlled benchmark protocol as a reusable template for comparing decision-making approaches.

arXiv:2609.13566v1 Announce Type: new Abstract: Industrial maintenance systems involve multiple interacting assets and shared resources, making it challenging to balance reliability and operational cost using a single decision framework. While recent work has focused on reinforcement learning RL for maintenance scheduling, direct comparisons with planning approaches under identical settings remain limited. In this work, we empirically compare planning and RL for multi-asset bearing maintenance using run-to-failure data. We examine how these methods behave when balancing preventive maintenance against tolerable failures across a range of failure penalty scenarios. We observed a consistent behavioral difference driven by objective formulation. Planning enforces reliability as a hard constraint and produces zero-failure policies whose total cost is largely insensitive to the magnitude of failure penalties. RL agents optimize expected cost and often trade off preventive maintenance against occasional failures as penalties vary, resulting in lower costs under low-penalty regimes but persistent non-zero failures even when penalties are high. We also investigate lightweight constraint mechanisms, including reward shaping and action masking, to encourage RL's reliability. From a practical perspective, planning may be more suitable when strict reliability is required and deployment horizons are short, whereas RL may provide cost-efficient policies when limited failures are acceptable and long-run operational efficiency is prioritized. Overall, this study clarifies the trade-offs between reliability and cost in multi-asset maintenance and suggests that planning and RL are complementary approaches. Beyond these findings, the controlled benchmark protocol itself that unifies environment, cost model, and evaluation across paradigms, offers a reusable template for comparing decision-making approaches in other maintenance settings.