Skip directly to content

The best performance so far on OpenAI Gym CarRacing

on Fri, 02/10/2023 - 18:43

Master student Irving Petrazzini, supervised by me, proposed PPO with the Beta distribution in 2021, surpassing the state-of-the-art on the CarRacing environment from OpenAI Gym. Check our paper for more details:

http://ericantonelo.com/research/proximal-policy-optimization-continuous-bounded-action-space-beta-distribution-342