mltandocker/gym repository overview

⁠Purpose

---

There is actually a way to install OpenAI-gym on Debian using apt-get and pip. Somehow most of the articles I found online describe the process of building from source code base on back-dated source-code, which is painfully long and error-prone. Hence this repo may ease all the pain and hazard during set-up on:

• Local computer Windows, MacOS, Linux : Ubuntu-16.04/18.04,LinuxMint-19, Debian-8/9 installed with Docker
• Free cloud's instances at https://labs.play-with-docker.com/⁠ (limited 3.9GiB disk space, recommended run on docker swarm mode, run with manager1 + worker1 by delete manager 2&3 + worker2 after create instances with 3 manager + 2 worker)
• AWS, Azure, Google Cloud, Kaggle&others (chargeable) but provide full speed and stability.

---

⁠Set Up One Algorithms (openai as good compare to deepmind) to beat all Atari-Games

• $ docker run -d --restart=always -p 8888:8888 mltandocker/gym
• Browser https://localhost:8888⁠, open jupyter notebook
• Read, Try Run Cells the 3 Google Tensor Flow Tutorial and move on to OpenAI-gym, click on CartPole.ipynb Run Cells
• Open the training_dir, reward end after approximately 500 steps
• Check, download training_dir, new envs will supersede previous training_dir.
• Replace Environment CartPole-vo, LunarLander-v2, MountainCar-v0, Breakout-ram-v0, SpaceInvaders-ram-v0 and etc.

---

⁠Included

This Notebook include debian pip install OpenAI-gym-universe installed with sample ipython CartpPole and tensorflow introduction machine learning tutorial. You can continue to install others packages and dependency, try out others envs(games) at https://gym.openai.com/envs/#atari⁠ and Enjoy !

⁠History of the Game Programming

OpenAI is a non-profit artificial intelligence (AI) research company that aims to promote and develop friendly AI in such a way as to benefit humanity as a whole. The organization aims to "freely collaborate" with other institutions and researchers by making its patents and research open to the public.The founders (notably Elon Musk and Sam Altman) are motivated in part by concerns about existential risk from artificial general intelligence.

Game programmers used to use heuristic if-then-else type decisions to make educated guesses. We saw this in the earliest arcade videos games such as Pong and PacMan. This trend was the norm for a very long time. But game developers can only predict so many scenarios and edge cases so your bot doesn’t run in circles!

Game developers then tried to mimic how humans would play a game, and modeled human intelligence in a game bot.

The team at DeepMind did this by generalizing and modeling intelligence to solve any Atari game thrown at it. The game bot used deep learning neural networks that would have no game-specific knowledge. They beat the game based on the pixels they saw on screen and their knowledge of the game controls. However, parts of DeepMind are still not open-sourced as Google uses it to beat competition.

Now you have the Game Bot ready to compete with the environment. Sweet & Happy Coding!

---

Please drop me email for whatever reason ? - [email protected]⁠ for discussion to advance AI!