You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
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.
Some algorithms of Reinforcement Learning implemented by me, in accordance to "Introduction to Reinforcement Learning" by Richard Sutton and Andrew Barto.
This module introduces temporal-difference learning and focuses on how it develops over the ideas of both Monte Carlo methods, and dynamic programming.
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.