This repository contains a PIP package which is an OpenAI environment for simulating an environment in which a magic-square is solved.
Install the OpenAI gym.
Then install this package via
pip install -e .
pip install gym
pip install tabulate
import gym import gym_magic env = gym.make('MagicSquare3x3-v0')
- Play the game
Part of the code for Deep-Q-Learning is based on this blog-post.
- "Human-level control through deep reinforcement learning", Nature 518 (7540), 529-533
- "Playing Atari with Deep Reinforcement Learning", preprint, arXiv:1312.5602
- Deep Reinforcement Learning Blog
- Tinker Brain's architecture
- Implement graphics window for
- For further improvement ideas check out these:
- Beat Atari with Deep Reinforcement Learning! (Part 1: DQN)
- Beat Atari with Deep Reinforcement Learning! (Part 2: DQN improvements)
- How to build your own AlphaZero AI using Python and Keras
- A Deep Dive into Reinforcement Learning
- OpenAI Baselines: DQN
- Frame Skipping and Pre-Processing for Deep Q-Networks on Atari 2600 Games