https://github.com/chagmgang/pysc2_rl

https://github.com/chagmgang/pysc2_rl

a2c advantage-actor-critic deep-learning deep-q-learning ppo proximal-policy-optimization pysc2 pysc2-mini-games reinfrocement-learning

Last synced: 3 months ago
JSON representation

• Host: GitHub
• URL: https://github.com/chagmgang/pysc2_rl
• Owner: chagmgang
• Created: 2018-05-01T11:02:39.000Z (over 7 years ago)
• Default Branch: master
• Last Pushed: 2018-07-14T15:52:51.000Z (about 7 years ago)
• Last Synced: 2025-04-22T12:37:50.643Z (6 months ago)
• Topics: a2c, advantage-actor-critic, deep-learning, deep-q-learning, ppo, proximal-policy-optimization, pysc2, pysc2-mini-games, reinfrocement-learning
• Language: Python
• Size: 6.65 MB
• Stars: 10
• Watchers: 0
• Forks: 0
• Open Issues: 2
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# pysc2_rl

DQN - https://github.com/chagmgang/OnlyDQNRL/tree/master/dqn

On-Policy A2C - https://github.com/chagmgang/OnlyPGRL/tree/master/actor_critic

ppo - https://github.com/chagmgang/OnlyPGRL/tree/master/policy_optimization

![Alt Text](https://github.com/chagmgang/pysc2_rl/blob/master/a2c_onpolicy.gif)

a2c_onplicy gif

![Alt Text](https://github.com/chagmgang/pysc2_rl/blob/master/cnn.gif)

ppo_cnn gif

![history_cnn_ppo](https://github.com/chagmgang/pysc2_rl/blob/master/ppo-cnn.PNG)

history of cnn ppo - time consumed to reach destination