Self-learning agents - Model evaluation for Tic-Tac-Toe

Self-Play Algorithms for Tic-Tac-Toe

Min-Max Search
Dynamic Programming
Q-Learning
Implementation in
- C++ / CUDA
- Python / Numpy / Tensorflow
Code - https://github.com/slabstech/tutorials/tree/main/algorithms
Steps
- Docker
  - docker build -t slabstech/tic-tac-toe .
  - docker run slabstech/tic-tac-toe
Reference
- JupyterNotebook + Docker + Tensorflow - https://dev.to/docker/machine-learning-with-tensorflow-object-detection-running-on-docker-5ek0
- https://github.com/rfeinman/tictactoe-reinforcement-learning
- Tensorflow - Docker - https://www.run.ai/guides/tensorflow/tensorflow-with-docker
- https://medium.com/@kaneel.senevirathne/teaching-agents-to-play-tic-tac-toe-using-reinforcement-learning-7a9d4d6ee9b3
- https://subscription.packtpub.com/book/data/9781838644147/11/ch11lvl1sec74/training-tic-tac-toe-agents-through-self-play
- https://ai.plainenglish.io/building-a-tic-tac-toe-game-with-reinforcement-learning-in-python-a-step-by-step-tutorial-5a6d9bcbb764
- https://towardsdatascience.com/an-ai-agent-plays-tic-tac-toe-part-1-building-the-opponent-to-play-against-bb5af74fded1