Continuous-Discrete Reinforcement Learning for Hybrid Control in Robotics

TL;DR

This paper introduces a hybrid reinforcement learning approach that simultaneously optimizes discrete and continuous actions in control problems, demonstrating efficiency and benefits over traditional methods in simulation and robotics.

Contribution

It presents a novel hybrid reinforcement learning method that handles native hybrid action spaces, avoiding simplifications and heuristics, and proposes reformulating control problems for better performance.

Findings

Efficiently solves hybrid RL problems in simulation and hardware.

Removes reliance on expert heuristics, improving control accuracy.

Encourages problem reformulation for exploration and wear reduction.

Abstract

Many real-world control problems involve both discrete decision variables - such as the choice of control modes, gear switching or digital outputs - as well as continuous decision variables - such as velocity setpoints, control gains or analogue outputs. However, when defining the corresponding optimal control or reinforcement learning problem, it is commonly approximated with fully continuous or fully discrete action spaces. These simplifications aim at tailoring the problem to a particular algorithm or solver which may only support one type of action space. Alternatively, expert heuristics are used to remove discrete actions from an otherwise continuous space. In contrast, we propose to treat hybrid problems in their 'native' form by solving them with hybrid reinforcement learning, which optimizes for discrete and continuous actions simultaneously. In our experiments, we first demonstrate that the proposed approach efficiently solves such natively hybrid reinforcement learning problems. We then show, both in simulation and on robotic hardware, the benefits of removing possibly imperfect expert-designed heuristics. Lastly, hybrid reinforcement learning encourages us to rethink problem definitions. We propose reformulating control problems, e.g. by adding meta actions, to improve exploration or reduce mechanical wear and tear.