Hierarchical Reinforcement Learning With Universal Policies for Multistep Robotic Manipulation

Multistep tasks, such as block stacking or parts (dis)assembly, are complex for autonomous robotic manipulation. A robotic system for such tasks would need to hierarchically combine motion control at a lower level and symbolic planning at a higher level. Recently, reinforcement learning (RL)-based methods have been shown to handle robotic motion control with better flexibility and generalizability. However, these methods have limited capability to handle such complex tasks involving planning and control with many intermediate steps over a long time horizon. First, current RL systems cannot achieve varied outcomes by planning over intermediate steps (e.g., stacking blocks in different orders). Second, the exploration efficiency of learning multistep tasks is low, especially when rewards are sparse. To address these limitations, we develop a unified hierarchical reinforcement learning framework, named Universal Option Framework (UOF), to enable the agent to learn varied outcomes in multistep tasks. To improve learning efficiency, we train both symbolic planning and kinematic control policies in parallel, aided by two proposed techniques: 1) an auto-adjusting exploration strategy (AAES) at the low level to stabilize the parallel training, and 2) abstract demonstrations at the high level to accelerate convergence. To evaluate its performance, we performed experiments on various multistep block-stacking tasks with blocks of different shapes and combinations and with different degrees of freedom for robot control. The results demonstrate that our method can accomplish multistep manipulation tasks more efficiently and stably, and with significantly less memory consumption.

I. Introduction

Humans solve complex manipulation tasks by dividing them into multiple steps. Similarly, for a robot to accomplish a task such as assembly, it is required to decompose the task into a sequence of intermediate steps, e.g., moving the gripper to a place, grasping an object, and placing the object. Such a decomposition enables different combinations and ordering of steps to achieve various desired outcomes.