LGAIROMay 23, 2023

GUARD: A Safe Reinforcement Learning Benchmark

arXiv:2305.13681v419 citations
Originality Synthesis-oriented
AI Analysis

This provides a standardized tool for researchers in safe RL to evaluate algorithms, though it is incremental as it builds on existing benchmarks.

The authors tackled the difficulty of comparing safe reinforcement learning algorithms due to diverse methods and tasks by introducing GUARD, a benchmark that includes a variety of agents, tasks, and safety constraints, and they established baselines for future work.

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. To fill that gap, we introduce GUARD, a Generalized Unified SAfe Reinforcement Learning Development Benchmark. GUARD has several advantages compared to existing benchmarks. First, GUARD is a generalized benchmark with a wide variety of RL agents, tasks, and safety constraint specifications. Second, GUARD comprehensively covers state-of-the-art safe RL algorithms with self-contained implementations. Third, GUARD is highly customizable in tasks and algorithms. We present a comparison of state-of-the-art safe RL algorithms in various task settings using GUARD and establish baselines that future work can build on.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes