A Generalized Reinforcement Learning Algorithm for Online 3D Bin-Packing

Authors: Richa Verma, Aniruddha Singhal, Harshad Khadilkar, Ansuma Basumatary, Siddharth Nayak, Harsh Vardhan Singh, Swagat Kumar and Rajesh Sinha

We attempt to solve the online version of the 3D bin-packing problem using reinforcement learning. Our method PackMan, beats heuristical methods in solving the task of filling the containers with boxes without the knowledge of the order of incoming box dimensions. [PDF], [slides]

Demo of boxes getting placed sequentially in 16 containers where each container is of size 45x80.