n-tuple-network

Here are 3 public repositories matching this topic...

halfrost / threes-ai

🏆 Threes! AI: deck-aware expectimax, N-tuple TD learning, and AlphaZero

golang reinforcement-learning game-engine deep-reinforcement-learning artificial-intelligence puzzle-game bitboard monte-carlo-tree-search 2048 game-ai threes expectimax value-function alphazero self-play temporal-difference-learning board-game-ai n-tuple-network

Updated Jul 28, 2026
Python

Aaronc123814 / 2048

Star

N-tuple TD-afterstate reinforcement learning agent for the game 2048 (~98% 2048, ~94% 4096, ~71% 8192 after 700k self-play episodes, CPU-only)

reinforcement-learning numba 2048 game-ai temporal-difference n-tuple-network afterstate

Updated May 11, 2026
Jupyter Notebook

od-89 / capped-2048-agent

Star

n-tuple network agent for capped 2048 — the game ends the instant a 2048 tile is made. Scores 50,484, and documents why twenty interventions failed to go higher.

reinforcement-learning cpp 2048 game-ai expectimax temporal-difference-learning n-tuple-network

Updated Aug 2, 2026
C++

Improve this page

Add a description, image, and links to the n-tuple-network topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

To associate your repository with the n-tuple-network topic, visit your repo's landing page and select "manage topics."

Learn more

Provide feedback

Saved searches

Use saved searches to filter your results more quickly