Implementation Matters in Deep RL: A Case Study on PPO and TRPODownload PDF

Published: 20 Dec 2019, Last Modified: 05 May 2023ICLR 2020 Conference Blind SubmissionReaders: Everyone
Keywords: deep policy gradient methods, deep reinforcement learning, trpo, ppo
Abstract: 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: https://github.com/implementation-matters/code-for-paper
Original Pdf: pdf
18 Replies

Loading