実装の違いが深層方策勾配法に与える影響：PPOとTRPOのケーススタディ
Implementation Matters in Deep Policy Gradients: A Case Study on PPO and TRPO
PPOとTRPOを比較し、実装上の細かな最適化が性能差の大部分を生み、RL手法の挙動を根本的に変えることを示した研究。
著者: Logan Engstrom, Andrew Ilyas, Shibani Santurkar, Dimitris Tsipras, Firdaus Janoos, Larry Rudolph, Aleksander Madry
分類: cs.LG, cs.RO, stat.ML
原文アブストラクト
We study the roots of algorithmic progress in deep policy gradient algorithms through a case study on two popular algorithms: Proximal Policy Optimization (PPO) and Trust Region Policy Optimization (TRPO). Specifically, we investigate the consequences of "code-level optimizations:" algorithm augmentations found only in implementations or described as auxiliary details to the core algorithm. Seemingly of secondary importance, such optimizations turn out to have a major impact on agent behavior. Our results show that they (a) are responsible for most of PPO's gain in cumulative reward over TRPO, and (b) fundamentally change how RL methods function. These insights show the difficulty and importance of attributing performance gains in deep reinforcement learning. Code for reproducing our results is available at https://github.com/MadryLab/implementation-matters .
