Measuring the Reliability of Reinforcement Learning Algorithms
This work addresses the reliability problem for RL researchers and production users, offering tools for evaluation and improvement, but it is incremental as it focuses on measurement rather than solving reliability directly.
The paper tackles the lack of reliability in reinforcement learning algorithms by proposing a set of metrics to quantitatively measure aspects like variability and risk during training and after learning, and applies these metrics to common RL algorithms and environments for comparison and analysis.
Lack of reliability is a well-known issue for reinforcement learning (RL) algorithms. This problem has gained increasing attention in recent years, and efforts to improve it have grown substantially. To aid RL researchers and production users with the evaluation and improvement of reliability, we propose a set of metrics that quantitatively measure different aspects of reliability. In this work, we focus on variability and risk, both during training and after learning (on a fixed policy). We designed these metrics to be general-purpose, and we also designed complementary statistical tests to enable rigorous comparisons on these metrics. In this paper, we first describe the desired properties of the metrics and their design, the aspects of reliability that they measure, and their applicability to different scenarios. We then describe the statistical tests and make additional practical recommendations for reporting results. The metrics and accompanying statistical tools have been made available as an open-source library at https://github.com/google-research/rl-reliability-metrics. We apply our metrics to a set of common RL algorithms and environments, compare them, and analyze the results.