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

2048 (3x3, 4x4, 5x5) AI
Developer: Jinyang Tang
Category: Games
~20.4K - 40.9K
409 ratings
2048 (3x3, 4x4, 5x5) AI icon

ASO Keyword Dashboard

Tracking 97 keywords for 2048 (3x3, 4x4, 5x5) AI in Apple App Store

Developer: Jinyang Tang Category: games Rating: 4.63

2048 (3x3, 4x4, 5x5) AI tracks 97 keywords (no keywords rank yet; 97 need traction). Key metrics: opportunity 47.9, difficulty 39.7.

Tracked keywords

97

0  ranked •  97  not ranking yet

Top 10 coverage

Best rank — • Latest leader —

Avg opportunity

47.9

Top keyword: best

Avg difficulty

39.7

Lower scores indicate easier wins

Opportunity leaders

  • best

    Opportunity: 59.0 • Difficulty: 59.6 • Rank —

    Competitors: 1,398

    85.9
  • create

    Opportunity: 59.0 • Difficulty: 60.6 • Rank —

    Competitors: 1,155

    84.7
  • like

    Opportunity: 59.0 • Difficulty: 63.2 • Rank —

    Competitors: 1,767

    87.6
  • features

    Opportunity: 59.0 • Difficulty: 60.4 • Rank —

    Competitors: 1,060

    83.9
  • puzzle

    Opportunity: 58.0 • Difficulty: 50.1 • Rank —

    Competitors: 447

    74.7

Unranked opportunities

  • best

    Opportunity: 59.0 • Difficulty: 59.6 • Competitors: 1,398

  • create

    Opportunity: 59.0 • Difficulty: 60.6 • Competitors: 1,155

  • like

    Opportunity: 59.0 • Difficulty: 63.2 • Competitors: 1,767

  • features

    Opportunity: 59.0 • Difficulty: 60.4 • Competitors: 1,060

  • puzzle

    Opportunity: 58.0 • Difficulty: 50.1 • Competitors: 447

High competition keywords

  • like

    Total apps: 7,508 • Major competitors: 1,767

    Latest rank: — • Difficulty: 63.2

  • best

    Total apps: 6,283 • Major competitors: 1,398

    Latest rank: — • Difficulty: 59.6

  • create

    Total apps: 5,537 • Major competitors: 1,155

    Latest rank: — • Difficulty: 60.6

  • features

    Total apps: 5,134 • Major competitors: 1,060

    Latest rank: — • Difficulty: 60.4

  • including

    Total apps: 3,880 • Major competitors: 926

    Latest rank: — • Difficulty: 62.0

All tracked keywords

Includes opportunity, difficulty, rankings and competitor benchmarks

Major Competitors
best591006086

6,283 competing apps

Median installs: 272,625

Avg rating: 4.6

1,398

major competitor apps

puzzle581005075

2,006 competing apps

Median installs: 275,850

Avg rating: 4.7

447

major competitor apps

strategy581004667

937 competing apps

Median installs: 252,800

Avg rating: 4.6

197

major competitor apps

action581004968

1,033 competing apps

Median installs: 300,175

Avg rating: 4.6

251

major competitor apps

art581004769

1,082 competing apps

Median installs: 239,212

Avg rating: 4.6

202

major competitor apps

version581004668

1,006 competing apps

Median installs: 238,775

Avg rating: 4.6

182

major competitor apps

order201006173

1,756 competing apps

Median installs: 288,212

Avg rating: 4.7

456

major competitor apps

environment571003859

397 competing apps

Median installs: 218,075

Avg rating: 4.6

63

major competitor apps

classic581005174

1,817 competing apps

Median installs: 292,025

Avg rating: 4.6

453

major competitor apps

used581005372

1,494 competing apps

Median installs: 237,800

Avg rating: 4.6

279

major competitor apps

limited581005565

715 competing apps

Median installs: 280,925

Avg rating: 4.6

171

major competitor apps

created581004767

953 competing apps

Median installs: 213,175

Avg rating: 4.6

153

major competitor apps

multiple581005478

2,846 competing apps

Median installs: 239,425

Avg rating: 4.6

550

major competitor apps

including581006281

3,880 competing apps

Median installs: 285,400

Avg rating: 4.6

926

major competitor apps

score201005268

977 competing apps

Median installs: 314,100

Avg rating: 4.7

264

major competitor apps

various581005075

2,177 competing apps

Median installs: 229,325

Avg rating: 4.6

374

major competitor apps

tree571003346

112 competing apps

Median installs: 295,300

Avg rating: 4.6

24

major competitor apps

search581006275

2,154 competing apps

Median installs: 273,038

Avg rating: 4.6

531

major competitor apps

move581005171

1,366 competing apps

Median installs: 278,150

Avg rating: 4.6

311

major competitor apps

understanding571003755

266 competing apps

Median installs: 199,150

Avg rating: 4.6

39

major competitor apps

technique571002638

48 competing apps

Median installs: 291,288

Avg rating: 4.7

10

major competitor apps

run581004770

1,204 competing apps

Median installs: 261,300

Avg rating: 4.6

249

major competitor apps

create591006185

5,537 competing apps

Median installs: 251,325

Avg rating: 4.6

1,155

major competitor apps

good581005271

1,413 competing apps

Median installs: 276,475

Avg rating: 4.6

294

major competitor apps

ai581005371

1,363 competing apps

Median installs: 253,250

Avg rating: 4.6

284

major competitor apps

97 keywords
1 of 4

App 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