Abstract
This document summarizes the efforts we made training an AI to play the popular PC game “Starcraft 2”, using Multi Agent deep reinforcement learning methods.
As part of our solution we have trained several variants of agents, using Multi agent methods to complete the game, and doing so, have managed to get better results than the baseline by about 25%. Our agents were trained using different Reinforcement Learning algorithms, namely DQN and A3C.
We have managed to get an average score of 78 compared to the 62 achieved by the baseline.
Achievements:
• Experimenting and learning different reinforcement learning algorithms
• Learning new reinforcement learning and deep learning algorithms
• Improving the baseline results using multi agent algorithms
