GUARD: A Safe Reinforcement Learning Benchmark

Understand

Due to the trial-and-error nature, it is typically challenging to apply RL algorithms to safety-critical real-world applications, such as autonomous driving, human-robot interaction, robot manipulation, etc, where such errors are not tolerable.

• Recently, safe RL (i.e.
• constrained RL) has emerged rapidly in the literature, in which the agents explore the environment while satisfying constraints.
• Due to the diversity of algorithms and tasks, it remains difficult to compare existing safe RL algorithms.