Advantage Actor-critic (A2C) and Proximal Policy Optimization (PPO) are popular deep reinforcement learning algorithms used for game AI in recent years. A common understanding is that A2C and PPO are separate algorithms because PPO's clipped objective appears significantly different than A2C's objective. In this paper, however, we show A2C is a special case of PPO. We present theoretical justifications and pseudocode analysis to demonstrate why. To validate our claim, we conduct an empirical experiment using \texttt{Stable-baselines3}, showing A2C and PPO produce the \textit{exact} same models when other settings are controlled.
@article{arxiv.2205.09123,
title = {A2C is a special case of PPO},
author = {Shengyi Huang and Anssi Kanervisto and Antonin Raffin and Weixun Wang and Santiago Ontañón and Rousslan Fernand Julien Dossa},
journal= {arXiv preprint arXiv:2205.09123},
year = {2022}
}