https://github.com/msokoloff1/asynchronous-advantage-actor-critic
Algorithm for learning how to perform tasks with only pixels and rewards as the agents understanding of the environment. The agent can learn how to play various atari games.
https://github.com/msokoloff1/asynchronous-advantage-actor-critic
a3c atari-games reinforcement-learning tensorflow
Last synced: about 1 month ago
JSON representation
Algorithm for learning how to perform tasks with only pixels and rewards as the agents understanding of the environment. The agent can learn how to play various atari games.
- Host: GitHub
- URL: https://github.com/msokoloff1/asynchronous-advantage-actor-critic
- Owner: msokoloff1
- Created: 2017-03-05T14:27:43.000Z (over 9 years ago)
- Default Branch: master
- Last Pushed: 2017-03-15T23:50:30.000Z (about 9 years ago)
- Last Synced: 2025-01-28T14:19:57.067Z (over 1 year ago)
- Topics: a3c, atari-games, reinforcement-learning, tensorflow
- Language: Python
- Size: 188 KB
- Stars: 3
- Watchers: 3
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Asynchronous-Advantage-Actor-Critic
Algorithm for learning how to perform tasks with only pixels and rewards as the agents understanding of the environment. The agent can learn how to play various atari games.
#####
I am currently cleaning up the code and training the model on other games. Once everything is production ready I will make a complete readme. For now, enjoy the gif!
