A set of AIs for the 2048 tile-merging game. Includes an expectimax strategy that reaches 16384 with 34.6% success and an ML model trained with temporal difference learning.

The Most Efficient Temporal Difference Learning Framework for 2048

A reinforcement learning framework for the game of Nim.

This repository contains my undergraduate thesis source code for Multi-stage Temporal Difference Learning with 2048 as an AI testbed. I reimagined my original C++ implementation in Qt for visualisation purposes.