Investigation of Factorized Optical Flows as Mid-Level Representations

Abstract

In this paper, we introduce a new concept of incorporating factorized flow maps as mid-level representations, for bridging the perception and the control modules in modular learning based robotic frameworks. To investigate the advantages of factorized flow maps and examine their interplay with the other types of mid-level representations, we further develop a configurable framework, along with four different environments that contain both static and dynamic objects, for analyzing the impacts of factorized optical flow maps on the performance of deep reinforcement learning agents. Based on this framework, we report our experimental results on various scenarios, and offer a set of analyses to justify our hypothesis. Finally, we validate flow factorization in real world scenarios.

Ting-Hsuan Liao, Hsu-Shen Liu, Li-Yuan Tsao, Tzu-Wen Wang, and Shan-Ya Yang contributed equally to this work, names listed in alphabetical order; This work has been submitted to the IEEE for possible publication

References in corpus (4)

• Soft Actor-Critic for Discrete Action Settings
• Discrete and Continuous Action Representation for Practical RL in Video Games
• Robust Policies via Mid-Level Visual Representations: An Experimental Study in Manipulation and Navigation
• Motion Perception in Reinforcement Learning with Dynamic Objects