RRLS : Robust Reinforcement Learning Suite
This provides a standardized benchmark for researchers in robust reinforcement learning, enabling reproducible and comparable experiments, though it is incremental as it builds on existing Mujoco environments.
They tackled the lack of standardized benchmarks in robust reinforcement learning by introducing the Robust Reinforcement Learning Suite (RRLS), which provides six continuous control tasks with uncertainty sets for training and evaluation, facilitating reproducible experiments.
Robust reinforcement learning is the problem of learning control policies that provide optimal worst-case performance against a span of adversarial environments. It is a crucial ingredient for deploying algorithms in real-world scenarios with prevalent environmental uncertainties and has been a long-standing object of attention in the community, without a standardized set of benchmarks. This contribution endeavors to fill this gap. We introduce the Robust Reinforcement Learning Suite (RRLS), a benchmark suite based on Mujoco environments. RRLS provides six continuous control tasks with two types of uncertainty sets for training and evaluation. Our benchmark aims to standardize robust reinforcement learning tasks, facilitating reproducible and comparable experiments, in particular those from recent state-of-the-art contributions, for which we demonstrate the use of RRLS. It is also designed to be easily expandable to new environments. The source code is available at \href{https://github.com/SuReLI/RRLS}{https://github.com/SuReLI/RRLS}.