Regularizing Action Policies for Smooth Control with Reinforcement Learning Abstract A critical problem with the practical utility of controllers trained with deep Reinforcement Learning (RL) is the notable lack of smoothness in the actions learned by the RL policies. This trend often presents itself in the form of control signal oscillation and can result in poor control, high power consumption, …
How to train your quadrotor
A Framework for Consistently Smooth and Responsive Flight Control via Reinforcement Learning Abstract We focus on the problem of reliably training Reinforcement Learning (RL) models (agents) for stable low-level control in embedded systems and test our methods on a high-performance, custom-built quadrotor platform. A common but often under-studied problem in developing RL agents for continuous control is that the control …
RT-Bench is an open-source framework that implements real-time features in a generic fashion, allowing different benchmarks to have the features out-of-the-box and accessible via a command line interface.
RT-Bench also provides an easy-to-use, unified command-line interface to customize key aspects of the real-time execution of a set of benchmarks.
Our framework is guided by four main criteria: 1) cohesive interface, 2) support for periodic application behavior and deadline semantics, 3) controllable memory footprint, and 4) extensibility and portability.