https://github.com/ackdav/drop7gym

Student Project: Openai Gym of Drop7
https://github.com/ackdav/drop7gym

drop7 gym-environment openai openai-gym python

Last synced: about 2 months ago
JSON representation

Student Project: Openai Gym of Drop7

• Host: GitHub
• URL: https://github.com/ackdav/drop7gym
• Owner: ackdav
• License: gpl-3.0
• Created: 2018-12-26T12:53:12.000Z (over 7 years ago)
• Default Branch: master
• Last Pushed: 2018-12-31T14:31:00.000Z (over 7 years ago)
• Last Synced: 2024-12-27T09:42:16.579Z (over 1 year ago)
• Topics: drop7, gym-environment, openai, openai-gym, python
• Language: Jupyter Notebook
• Homepage:
• Size: 665 KB
• Stars: 0
• Watchers: 2
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# Drop7Gym

This is the RL project of group "State Space Invaders" for the course 

"Reinforcement Learning" in Fall '18.

The code base for the game partly relies on:

[this repo](https://github.com/Ram-N/Drop7). We refactored the code heavily, adapted 

the environment format of [OpenAI Gym](https://gym.openai.com/) and adjusted core mechanics, 

to adjust to the true state of the game.

Please refer to the folder "notebooks" for the following items: 

- "Introduction": Outlining the environment and how to use it.

- "Random Benchmark": Describing an Agent that takes random actions each move.

- "DQN": Training of a DQN model and describing the result.

- "Policy Gradient": Training of a Policy Gradient model and describing the result.