Project in Basics of Computer Intelligence (ORI) in Faculty of Technical Sciences in Novi Sad, Serbia.
Done by: Mihajlo Maksimovic, RA92/2019
The project is written in Python using TensorFlow for building a deep Q-network.
Implemented:
Open AI Gym Acrobot solution using a Deep Q-Network created with TensorFlow. In 100 episodes, the agent consistently reaches a score around -100.
The agent in action:
Progression of rewards for each episode:
