Space Invaders is a part of the Atari environments, its objective is to destroy the space invaders by shooting its laser cannon and avoiding shooting targets from the invaders. The agent has six actions, and the optimal solution is as mentioned before (i.e., to destroy the invaders). We have found an interesting paper published by Google DeepMind, in which they improved the performance of regular DQN (Deep Q-Network) by 164.11%. We also found some promising algorithms that worth a shot, such as Keras-RL and PPO-LSTM included in Stable-Baselines3 community contribution.
-
Notifications
You must be signed in to change notification settings - Fork 0
SaraElfetiany/Space_Invaders
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
About
Queen's University - Reinforcement Learning (CISC 856)
Topics
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published