2048 (3x3, 4x4, 5x5) AI 6.5



Publisher 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

Sep 26, 2023
Version 6.5
Some bug fixes.


About 2048 (3x3, 4x4, 5x5) AI

2048 (3x3, 4x4, 5x5) AI is a free app for iOS published in the Action list of apps, part of Games & Entertainment.

The company that develops 2048 (3x3, 4x4, 5x5) AI is Jinyang Tang. The latest version released by its developer is 6.5.

To install 2048 (3x3, 4x4, 5x5) AI on your iOS device, just click the green Continue To App button above to start the installation process. The app is listed on our website since 2023-09-26 and was downloaded 1 times. We have already checked if the download link is safe, however for your own protection we recommend that you scan the downloaded app with your antivirus. Your antivirus may detect the 2048 (3x3, 4x4, 5x5) AI as malware if the download link is broken.

How to install 2048 (3x3, 4x4, 5x5) AI on your iOS device:

  • Click on the Continue To App button on our website. This will redirect you to the App Store.
  • Once the 2048 (3x3, 4x4, 5x5) AI is shown in the iTunes listing of your iOS device, you can start its download and installation. Tap on the GET button to the right of the app to start downloading it.
  • If you are not logged-in the iOS appstore app, you'll be prompted for your your Apple ID and/or password.
  • After 2048 (3x3, 4x4, 5x5) AI is downloaded, you'll see an INSTALL button to the right. Tap on it to start the actual installation of the iOS app.
  • Once installation is finished you can tap on the OPEN button to start it. Its icon will also be added to your device home screen.



RELATED PROGRAMS
Our Recommendations






BarCode2D-PNG


Click stars to rate this APP!

Users Rating:  
  0.0/5     0
Downloads: 1
Updated At: 2024-03-04
Publisher: Jinyang Tang
Operating System: Ios
License Type: Free