Learn to Floorplan through Acquisition of Effective Local Search Heuristics
| Autor: | Peiyu Liao, Martin D.F. Wong, Ngai Wong, Bei Yu, Zhuolun He, Yuzhe Ma, Lu Zhang |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Sequence
Computer science business.industry Heuristic 02 engineering and technology 010501 environmental sciences Machine learning computer.software_genre 01 natural sciences Floorplan 0202 electrical engineering electronic engineering information engineering Reinforcement learning 020201 artificial intelligence & image processing Local search (optimization) Artificial intelligence Heuristics business computer 0105 earth and related environmental sciences |
| Zdroj: | ICCD |
| DOI: | 10.1109/iccd50377.2020.00061 |
| Popis: | Automatic heuristic design through reinforcement learning opens a promising direction for solving computationally difficult problems. Unlike most previous works that aimed at solution construction, we explore the possibility of acquiring local search heuristics through massive search experiments. To illustrate the applicability, an agent is trained to perform a walk in the search space by selecting a candidate neighbor solution at each step. Specifically, we target the floorplanning problem, where a neighbor solution is generated through perturbing the sequence pair encoding of a floorplan. Experimental results demonstrate the efficacy of the acquired heuristics as well as the potential of automatic heuristic design. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|