Supplementary Material for " Brick-by-Brick: Combinatorial Construction with Deep Reinforcement Learning " 1 1 23 14Hyunsoo Chung Jungtaek 23 Kim Boris

In this material, we first describe the importance of action validity prediction networks. Then, we introduce the details of the benchmarks, provide the model architecture, and present the additional experimental results, which are missing in the main article. We present the results of wall-clock time for computing the ground-truth action validity in Figure s.1. It shows that computing the action validity for a combination of 100 bricks needs more than 20 seconds. Moreover, we summarize the comparisons between possible action validation approaches as shown in Table s.1.0