An implementation of a PPO agent capable of acting in the MircroRaces environment. The project was developed for the Machine Learning course of the University of Bologna.
Link to the MicroRacer environment : https://github.com/asperti/MicroRacer
Tha PPO algorithm is also inspired by the following papers and docs:
[1] https://keras.io/examples/rl/ppo_cartpole/
[2] https://arxiv.org/pdf/1707.06347.pdf