Project information
The project consists in testing the algorithm on an environment that is assigned to us and analyze the data that it is working in that environment. In this project, we use Reinforcement Learning, which is a technique that allows the agent to learn a certain behavior depending on the environment submit to it with methods based on the concept of reward. In my case, I was given the DQN algorithm to test on Assault environment of OpenAi Gym. The algorithm was provided to us using the ”stable baselines” library.
