Implementation Matters In Deep Policy Gradients: A Case Study On PPO And TRPO

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 for reproducing our results is available at https://github.com/MadryLab/implementation-matters .

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyengstrom2020implementation

Code

• MadryLab/implementation-matters—

Related papers

• Revisiting Design Choices In Proximal Policy Optimization (2020)0.00
• Proximal Policy Optimization Algorithms (2017)0.00
• Truly Proximal Policy Optimization (2019)0.00
• Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization (2018)0.00
• Neural Proximal/trust Region Policy Optimization Attains Globally Optimal Policy (2019)0.00
• Simple Policy Optimization (2024)0.00
• TIC-GRPO: Provable And Efficient Optimization For Reinforcement Learning From Human Feedback (2025)0.00
• On Proximal Policy Optimization's Heavy-tailed Gradients (2021)0.00