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

Towards explainable value functions in reinforcement learning. A framework for collision probability distribution estimation via deep temporal difference learning.

Solutions for course: "Applied Game Theory" taken at University of Novi Sad - Faculty of Technical Sciences

A reinforcement learning framework for the game of Nim.

Temporal difference learning for 2048

This module introduces temporal-difference learning and focuses on how it develops over the ideas of both Monte Carlo methods, and dynamic programming.

Some algorithms of Reinforcement Learning implemented by me, in accordance to "Introduction to Reinforcement Learning" by Richard Sutton and Andrew Barto.

My Implementation of the Accelerated Gradient Temporal Difference Learning algorithm in Python

Course work for CSE 574 Planning and Learning Methods in AI

Reinforcement learning methods applied for navigation

A Reinforcement Learning library for solving custom environments

Tabular TD control in MAZE environment using Q-Learning, SARSA, and Expected SARSA

🧗 Navigates a grid-world environment using SARSA Reinforcement Learning. Features on-policy path optimization.

Roskilde University, 2nd semester project (AI - Reinforcement Learning)

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.

Q-learning and SARSA playing ludo.

This RL project aims to make robot navigate from start to an end goal. Two cases for continuous and discrete action spaces are implemented.

University of Tehran-Reinforcement Learning Fall 2022

SuPeReInFoRzE is a cutting-edge RL framework for Super TTT. The system combines multiple AI paradigms to create agents capable of human-expert level play through: ⚡ Temporal Difference Learning (Q-Learning with Experience Replay) 🌲 Monte Carlo Tree Search🎯 Minimax with Alpha-Beta Pruning 🧮 Advanced Heuristic Evaluation