Skip to content

v1.0 - Algortihm Generation and Deep RL training

Latest
Compare
Choose a tag to compare
@simulatedScience simulatedScience released this 30 Nov 12:53
· 6 commits to main since this release

This version implements automatic algorithm generation and symmetry detection for puzzles. It also includes tools to train, test and analyze deep reinforcement learning agents for solving general twisty puzzles.
This version includes many new puzzles, some ready-to-use trained neural networks for solving six different puzzles and several new CLI commands to improve the user experience.