Tutor-Guided Interior Navigation With Deep Reinforcement Learning

Traditional reinforcement learning makes policy based on the current system state. However, insufficient system information and few rewards lead to its limited applicability, especially in a partially observed environment with sparse rewards. In this work, we propose a tutor-student network (TSN) for improving an agent's performance with additional auxiliary information. In the tutor-student framework, a tutor module generates auxiliary information, while a student module refers to the tutor's suggestion during training. The key of our proposed approach is that tutor provides prior knowledge that does not correspond to a specified environment to help the student module accelerate the learning procedure. We build 12 indoor mazes in ViZDoom, including empty mazes and mazes with obstacles, evaluate the performance of TSN compared with advantage actor-critic (A2C) and show that the proposed network learned navigation faster and obtained higher accumulated rewards. More importantly, our approach could generalize well to new and unseen domains.