EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Uncertainty-Aware Congestion Reward Shaping for Multi-Objective IC Placement with Deep Reinforcement Learning

Xinyi Wei, Michael Ghosh, Hiro Sharma, Qian Wei

International Journal of Mechanical and Electrical Engineering · 04.11.2026 · 8 (7) · 48-60

DOI: 10.62051/ijmee.v8n7.06 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Mechanical and Electrical Engineering, online erschienen am 04.11.2026. Verfasst von Xinyi Wei und 3 weiteren Autor:innen. Die Arbeit nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Reinforcement-learning (RL) placers increasingly use learned congestion predictors to densify their reward through potential-based shaping. Existing congestion-aware shaping evaluates an overflow penalty at a point prediction of the final routing demand, although this demand is uncertain while objects remain unplaced and the predictor is unreliable on unfamiliar states. We show that the plug-in potential is optimistically biased by Jensen’s inequality, most strongly early in an episode, and propose UA-CARS: a deep ensemble of heteroscedastic grid-graph GCNs predicts the final g-cell utilisation, the expected overflow penalty is evaluated in closed form, and the potential is shrunk toward a reference potential with a precision weight derived from ensemble disagreement, which preserves policy invariance and adds no tuning parameter. On four OpenROAD designs built from public gate-level netlists, the uncertainty-aware potentials reduce the error of the congestion-to-go estimate by 32–36% and lower their trust automatically where the predictor generalizes poorly. A controlled PPO study with 56 training runs shows, however, that potential accuracy alone does not yield better placements: with a neutral reference, UA-CARS performs on par with the plug-in baseline, and both are outperformed by the exact incremental congestion reward. Anchoring the shrinkage on that reward (UA-CARS-M) matches it and lowers the late-training cost of CARS by 5.6% (11/12 design–seed pairs, p=0.002). We trace these results to the accuracy of potential differences, which governs the benefit of shaping.

Zitieren

APA

Wei, X., Ghosh, M., Sharma, H., & Wei, Q. (2026). Uncertainty-Aware Congestion Reward Shaping for Multi-Objective IC Placement with Deep Reinforcement Learning. International Journal of Mechanical and Electrical Engineering, 8(7), 48-60. https://doi.org/10.62051/ijmee.v8n7.06

Vancouver

Wei X, Ghosh M, Sharma H, Wei Q. Uncertainty-Aware Congestion Reward Shaping for Multi-Objective IC Placement with Deep Reinforcement Learning. International Journal of Mechanical and Electrical Engineering. 2026;8(7):48-60. doi:10.62051/ijmee.v8n7.06

BibTeX
@article{Wei2026,
  author = {Wei, Xinyi and Ghosh, Michael and Sharma, Hiro and Wei, Qian},
  title = {Uncertainty-Aware Congestion Reward Shaping for Multi-Objective IC Placement with Deep Reinforcement Learning},
  journal = {International Journal of Mechanical and Electrical Engineering},
  year = {2026},
  volume = {8},
  number = {7},
  pages = {48--60},
  doi = {10.62051/ijmee.v8n7.06}
}
Kostenlos starten →