# IR-Aware ECO Timing Optimization Using Reinforcement Learning

arXiv: https://arxiv.org/abs/2402.07781 · HTML: https://mlsanity.com/paper/2402.07781/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in RL for energy, networks and operations, one of 15 directions in Deep reinforcement learning methods.
- Builds on 3 of its 24 references that are in the map.
- First posted on arXiv 12 Feb 2024.

## 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, 3 of 3)

- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [Convex optimization](https://mlsanity.com/paper/2106.01946/) (2021)
- [GCN-RL Circuit Designer: Transferable Transistor Sizing with Graph Neural Networks and Reinforcement Learning](https://mlsanity.com/paper/2005.00406/) (2020)

## Built on by (most cited first, 4 of 4)

- [Unsupervised Graph Neural Network Framework for Balanced Multipatterning in Advanced Electronic Design Automation Layouts](https://mlsanity.com/paper/2511.16374/) (2025)
- [TicTacBench: Benchmarking Timing Closure Capabilities of Coding Agents](https://mlsanity.com/paper/2609.23363/) (2026)
- [WaveletECO: A Closed-Loop Physical ECO Platform and a Specialized Local Language Model](https://mlsanity.com/paper/2609.23444/) (2026)
- [AI-Driven, Timing-Aware Power Optimization](https://mlsanity.com/paper/2610.18890/) (2026)

## Abstract (arXiv)

Engineering change orders (ECOs) in late stages make minimal design fixes to recover from timing shifts due to excessive IR drops. This paper integrates IR-drop-aware timing analysis and ECO timing optimization using reinforcement learning (RL). The method operates after physical design and power grid synthesis, and rectifies IR-drop-induced timing degradation through gate sizing. It incorporates the Lagrangian relaxation (LR) technique into a novel RL framework, which trains a relational graph convolutional network (R-GCN) agent to sequentially size gates to fix timing violations. The R-GCN agent outperforms a classical LR-only algorithm: in an open 45nm technology, it (a) moves the Pareto front of the delay-power tradeoff curve to the left (b) saves runtime over the prior approaches by running fast inference using trained models, and (c) reduces the perturbation to placement by sizing fewer cells. The RL model is transferable across timing specifications and to unseen designs with fine tuning.