An agent learns to play Tetris through reinforcement learning. The primary algorithm for the agent is Monte Carlo Tree Search (MCTS), a heuristic search algorithm commonly used for games. The implementation uses a screen capture of a Tetr.io window to directly input moves into the game.
An agent learns to play Tetris through reinforcement learning
License
SanjayVijay27/tetris-rl
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
About
An agent learns to play Tetris through reinforcement learning
Resources
License
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published