Circuit Routing Using Deep Reinforcement Learning and Tree Search
Circuit routing is a fundamental problem in designing electronic systems such as integrated circuits (ICs) and printed circuit boards (PCBs) which form the hardware of electronics and computers. Like finding paths between pairs of locations, circuit routing generates traces of wires to connect contacts or leads of circuit components. It is challenging because finding paths between dense and massive electronic components involves a very large search space. Existing solutions are either manually designed with domain knowledge or tailored to specific constraints in the circuit design, hence, difficult to adapt to new problems or design needs. We model the circuit routing as a sequential decision-making problem, and solve it by using reinforcement learning and tree search algorithms.
Committee: Forrest Sheng Bao (major professor), Carl K. Chang, David Fernandez-Baca, Jin Tian, and Mai Zheng.