Imitation Learning for Simultaneous Escape Routing

Kim, Minsu; Park, Hyunwook; Son, Keeyoung; Kim, Seongguk; Kim, Haeyeon; Kim, Jihun; Song, Jinwook; Ku, Youngmin; Park, Jounggyu; Kim, Joungho

doi:10.1109/epeps51341.2021.9609145

Cited by 3 publications

(3 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…All experiments were performed using a single NVIDIA A100 GPU and an AMD EPYC 7542 32-core processor as the CPU. Comparing the speed performance of classical algorithms (CPU-oriented) and learning algorithms (GPU-oriented) poses a significant challenge (Kool, van Hoof, and Welling 2019;Kim, Park, and Kim 2021), given the need for a fair evaluation. While certain approaches exploit the parallelizability of learning algorithms on GPUs, enabling faster solutions to multiple problems than classical algorithms, our method follows a serial approach in line with the prior min-max learning methods (Park, Kwon, and Park 2023;Kim, Park, and Park 2023).…”

Section: Methodsmentioning

confidence: 99%

“…Independent of constructive solution generation, other studies try to solve VRPs by learning to revise the solution iteratively, terms improvement solver. Chen and Tian (2019); Li, Yan, and Wu (2021); Kim, Park, and Kim (2021); Wang et al (2021) leverages local solver to rewrite partial tour to improve solution. Some studies train existing local search solvers such as 2-opt heuristic (da Costa et al 2020;Wu et al 2021), large neighborhood search (Hottung and Tierney 2020), iterative dynamic programming (Kool et al 2021), and LKH (Xin et al 2021b) using deep learning.…”

Section: Related Work Vehicle Routing Problemsmentioning

confidence: 99%

See 1 more Smart Citation

Equity-Transformer: Solving NP-Hard Min-Max Routing Problems as Sequential Generation with Equity Context

Son,

Kim,

Choi

et al. 2024

AAAI

View full text Add to dashboard Cite

Min-max routing problems aim to minimize the maximum tour length among multiple agents as they collaboratively visit all cities, i.e., the completion time. These problems include impactful real-world applications but are known as NP-hard. Existing methods are facing challenges, particularly in large-scale problems that require the coordination of numerous agents to cover thousands of cities. This paper proposes Equity-Transformer to solve large-scale min-max routing problems. First, we model min-max routing problems into sequential planning, reducing the complexity and enabling the use of a powerful Transformer architecture. Second, we propose key inductive biases that ensure equitable workload distribution among agents. The effectiveness of Equity-Transformer is demonstrated through its superior performance in two representative min-max routing tasks: the min-max multi-agent traveling salesman problem (min-max mTSP) and the min-max multi-agent pick-up and delivery problem (min-max mPDP). Notably, our method achieves significant reductions of runtime, approximately 335 times, and cost values of about 53% compared to a competitive heuristic (LKH3) in the case of 100 vehicles with 1,000 cities of mTSP. We provide reproducible source code: https://github.com/kaist-silab/equity-transformer.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Related Work Vehicle Routing Problemsmentioning

confidence: 99%

Equity-Transformer: Solving NP-Hard Min-Max Routing Problems as Sequential Generation with Equity Context

Son,

Kim,

Choi

et al. 2024

AAAI

View full text Add to dashboard Cite

show abstract

“…Ma et al [8] applied Negotiated Congestion [9] which was widely used in FPGA and IC to solve this problem. Works in [10][11][12] divided SER problem into two steps: net sort and escape. The result of escape will be constrained with net sort.…”

Section: Related Workmentioning

confidence: 99%

Simultaneous escape routing based on multi-commodity flow

Shao

2023

Third International Conference on Artificial Intelligence and Computer Engineering (ICAICE 2022)

View full text Add to dashboard Cite

As size of pin arrays increases significantly, Printed Circuit Board routing becomes an arduous and challenging problem. Traditional manual routing might cost a lot of time. Simultaneous escape routing is a routing problem based on multiple pin arrays, and it's an important stage of PCB routing. In this paper, we propose a novel algorithm to solve the SER problem based on Multi-Commodity Flow. Experimental results show that our method can obtain shorter wire length and use less boundary resources than other methods.

show abstract

Bayesian Exploration Imitation Learning-Based Contextual via Design Optimization Method of PAM-4-Based High-Speed Serial Link

Kim,

Kim

et al. 2023

IEEE Trans. Electromagn. Compat.

View full text Add to dashboard Cite

Imitation Learning for Simultaneous Escape Routing

Cited by 3 publications

References 7 publications

Equity-Transformer: Solving NP-Hard Min-Max Routing Problems as Sequential Generation with Equity Context

Equity-Transformer: Solving NP-Hard Min-Max Routing Problems as Sequential Generation with Equity Context

Simultaneous escape routing based on multi-commodity flow

Bayesian Exploration Imitation Learning-Based Contextual via Design Optimization Method of PAM-4-Based High-Speed Serial Link

Contact Info

Product

Resources

About