Tailoring PPO algorithm to Enduro
Abstract
This research consists in tailoring the PPO algorithm, used in reinforcement learning, to train an agent to the Atari game Enduro.The experiments consisted in running the agent with unique seeds 30 times and comparing to a baseline its performance with reward shaping and observation layer modification.
Fields of Study & Subjects
Reinforcement Learning in Robotics
Artificial Intelligence in Games
Artificial Intelligence Applications
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 6 February 2026
- Language
- EN