Low-cost Real-world Implementation of the Swing-up Pendulum for Deep Reinforcement Learning Experiments
This provides an accessible educational tool for researchers and students to explore sim-to-real DRL methods, though it is incremental as it builds on existing pendulum setups.
The authors tackled the sim-to-real gap in deep reinforcement learning by developing a low-cost physical inverted pendulum apparatus and software environment, enabling detailed examination of delays in physical systems and reducing costs to under $200 using off-the-shelf components.
Deep reinforcement learning (DRL) has had success in virtual and simulated domains, but due to key differences between simulated and real-world environments, DRL-trained policies have had limited success in real-world applications. To assist researchers to bridge the \textit{sim-to-real gap}, in this paper, we describe a low-cost physical inverted pendulum apparatus and software environment for exploring sim-to-real DRL methods. In particular, the design of our apparatus enables detailed examination of the delays that arise in physical systems when sensing, communicating, learning, inferring and actuating. Moreover, we wish to improve access to educational systems, so our apparatus uses readily available materials and parts to reduce cost and logistical barriers. Our design shows how commercial, off-the-shelf electronics and electromechanical and sensor systems, combined with common metal extrusions, dowel and 3D printed couplings provide a pathway for affordable physical DRL apparatus. The physical apparatus is complemented with a simulated environment implemented using a high-fidelity physics engine and OpenAI Gym interface.