Evaluating the Performance of Reinforcement Learning Algorithms

Abstract

Performance evaluations are critical for quantifying algorithmic advances in reinforcement learning. Recent reproducibility analyses have shown that reported performance results are often inconsistent and difficult to replicate. In this work, we argue that the inconsistency of performance stems from the use of flawed evaluation metrics. Taking a step towards ensuring that reported results are consistent, we propose a new comprehensive evaluation methodology for reinforcement learning algorithms that produces reliable measurements of performance both on a single environment and when aggregated across environments. We demonstrate this method by evaluating a broad class of reinforcement learning algorithms on standard benchmark tasks.

30 pages, 9 figures, Thirty-seventh International Conference on Machine Learning (ICML 2020)

Cited by in corpus (6)

• Automated Reinforcement Learning (AutoRL): A Survey and Open Problems
• Deep Reinforcement Learning at the Edge of the Statistical Precipice
• Evaluating the Robustness of Off-Policy Evaluation
• Low-Precision Reinforcement Learning: Running Soft Actor-Critic in Half Precision
• A Distance-based Anomaly Detection Framework for Deep Reinforcement Learning
• General Characterization of Agents by States they Visit