![](/assets/artwork/1x1-42817eea7ade52607a760cbee00d1495.gif)
2048 (3x3, 4x4, 5x5) AI 4+
1024 -> 2048 -> 4096
Jinyang Tang
-
- Free
Screenshots
Description
Classic 2048 puzzle game redefined by AI.
Our 2048 is one of its own kind in the market. We leverage multiple algorithms to create an AI for the classic 2048 puzzle game.
* Redefined by AI *
We created an AI that takes advantage of multiple state-of-the-art algorithms, including Monte Carlo Tree Search (MCTS) [a], Expectimax [b], Iterative Deepening Depth-First Search (IDDFS) [c] and Reinforcement Learning [d].
(a) Monte Carlo Tree Search (MCTS) is a heuristic search algorithm introduced in 2006 for computer Go, and has been used in other games like chess, and of course this 2048 game. Monte Carlo Tree Search Algorithm chooses the best possible move from the current state of game's tree (similar to IDDFS).
(b) Expectimax search is a variation of the minimax algorithm, with addition of "chance" nodes in the search tree. This technique is commonly used in games with undeterministic behavior, such as Minesweeper (random mine location), Pacman (random ghost move) and this 2048 game (random tile spawn position and its number value).
(c)Iterative Deepening depth-first search (IDDFS) is a search strategy in which a depth-limited version of DFS is run repeatedly with increasing depth limits. IDDFS is optimal like breadth-first search (BFS), but uses much less memory. This 2048 AI implementation assigns various heuristic scores (or penalties) on multiple features (e.g. empty cell count) to compute the optimal next move.
(d) Reinforcement learning is the training of ML models to yield an action (or decision) in an environment in order to maximize cumulative reward. This 2048 RL implementation has no hard-coded intelligence (i.e. no heuristic score based on human understanding of the game). There is no knowledge about what makes a good move, and the AI agent "figures it out" on its own as we train the model.
References:
[a] https://www.aaai.org/Papers/AIIDE/2008/AIIDE08-036.pdf
[b] http://www.jveness.info/publications/thesis.pdf
[c] https://cse.sc.edu/~MGV/csce580sp15/gradPres/korf_IDAStar_1985.pdf
[d] http://rail.eecs.berkeley.edu/deeprlcourse/static/slides/lec-8.pdf
What’s New
Version 6.5
Some bug fixes.
Ratings and Reviews
Es muy buena aplicación
Es muy divertida y tiene muchas utilidades, pero len doy 4 estrellas porque es demasiado intensa en anuncios
Developer Response ,
Hi, I have recently reduced ad frequency (and will keep reducing it in upcoming updates). Please download the latest version. Thanks.
Súper entretenido
Muy entretenido y muy completa ideal para viajes, y esperas en ratos muertos.
App Privacy
The developer, Jinyang Tang, indicated that the app’s privacy practices may include handling of data as described below. For more information, see the developer’s privacy policy.
Data Used to Track You
The following data may be used to track you across apps and websites owned by other companies:
- Location
- Identifiers
- Usage Data
- Diagnostics
Data Linked to You
The following data may be collected and linked to your identity:
- Location
- Identifiers
- Usage Data
- Diagnostics
Data Not Linked to You
The following data may be collected but it is not linked to your identity:
- Diagnostics
Privacy practices may vary based on, for example, the features you use or your age. Learn More
Information
- Provider
- Jinyang Tang
- Size
- 148.9 MB
- Category
- Games
- Compatibility
-
- iPhone
- Requires iOS 17.0 or later.
- iPad
- Requires iPadOS 17.0 or later.
- Apple Vision
- Requires visionOS 1.0 or later.
- Languages
-
English, Arabic, Catalan, Croatian, Czech, Danish, Dutch, Finnish, French, German, Greek, Hebrew, Hindi, Hungarian, Indonesian, Italian, Japanese, Korean, Malay, Norwegian Bokmål, Polish, Portuguese, Romanian, Russian, Simplified Chinese, Slovak, Spanish, Swedish, Thai, Traditional Chinese, Turkish, Ukrainian, Vietnamese
- Age Rating
- 4+
- Copyright
- © 2021 YZ
- Price
- Free
Supports
-
Game Center
Challenge friends and check leaderboards and achievements.