---
title: "The Successful Ingredients of Policy Gradient Algorithms"
authors:
  - "Sven Gronauer"
  - "Martin Gottwald"
  - "Klaus Diepold"
doi: "10.24963/ijcai.2021/338"
url: "https://ijcai.org/proceedings/2021/338"
pdf: "https://ijcai.org/proceedings/2021/0338.pdf"
venue: "Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence"
year: 2021
pages: "2455-2461"
track: "Main Track"
keywords:
  - "Multidisciplinary Topics and Applications: Validation and Verification"
  - "Machine Learning: Deep Reinforcement Learning"
  - "AI Ethics, Trust, Fairness: Reproducibility"
---

# The Successful Ingredients of Policy Gradient Algorithms

Sven Gronauer, Martin Gottwald, Klaus Diepold

*Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence*, pages 2455-2461. DOI: [10.24963/ijcai.2021/338](https://doi.org/10.24963/ijcai.2021/338)

## Abstract

Despite the sublime success in recent years, the underlying mechanisms powering the advances of reinforcement learning are yet poorly understood. In this paper, we identify these mechanisms - which we call ingredients - in on-policy policy gradient methods and empirically determine their impact on the learning. To allow an equitable assessment, we conduct our experiments based on a unified and modular implementation. Our results underline the significance of recent algorithmic advances and demonstrate that reaching state-of-the-art performance may not need sophisticated algorithms but can also be accomplished by the combination of a few simple ingredients.