JamesMcGuigan / ai-games

Artifical Intelligence Game Solving Agents

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Artificial Intelligence Games

Games

ConnectX

Writeup on a variety of approaches to competitive AI agent design, exploring classic game: Connect 4

  • Random Agent
  • Simple Rules Agent
  • Minimax with AlphaBeta Pruning, Iterative Deepening and custom heuristic
    • Object Oriented / Numpy implementation (slow)
    • Bitboard Implementation (fast)

Knights Isolation

Minimax adversarial search with alphaBeta pruning, iterative deepening, area heuristic, and persistent caching.

Monty Carlo Tree Search reinforcement learning

Search

Ant Colony Optimization Algorithm with Kmeans

Ant Colony Solution the Travelling Salesman Problem

ARC - Abstraction and Reasoning Corpus

ARC can be seen as a general artificial intelligence benchmark, as a program synthesis benchmark, or as a psychometric intelligence test. It is targeted at both humans and artificially intelligent systems that aim at emulating a human-like form of general fluid intelligence.

Object model and frameworks for reasoning by analogy function solvers.

Brute force search of simple geometry and tessellation transformations with numpy.

XGBoost with a large multidimensional feature map was able to auto-solve a wide range of transformations.

AbstractSolver - Proof of Concept code using inspect.signature() to figure out all possible permutations of f(g(h(x))) implementing a IoC dependency injection solver.

Pacman - A* Search

A* Search Algorithms to navigate Pacman round a maze

Puzzles

Sudoku

Sudoku Solver that can solve the World's Hardest Sudoku

N Queens

This code solves the N-Queens problem in Prolog using the CLP(FD): Constraint Logic Programming over Finite Domain Library

Cryptarithmetic

This is a general purpose solver that can handle addition, subtraction, multiplication, integer division and raising to powers.

About

Artifical Intelligence Game Solving Agents


Languages

Language:Jupyter Notebook 82.2%Language:Python 17.7%Language:Shell 0.0%Language:Prolog 0.0%Language:Dockerfile 0.0%