A2C is a special case of PPO

05/18/2022

∙

by   Shengyi Huang, et al.

∙

11

∙

share

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 , showing A2C and PPO produce the exact same models when other settings are controlled.