Games like Dyna-Q: Agents that can plan

About In this simulation, I train an agent to balance a ball that is launched onto a platform, avoiding the machinery below for 15 seconds. Despite the task appearing straightforward, it presents a couple of new challenges that haven't been in my previous agents. This agent uses Q-Learning with linear function approximation and  tile coding to handle the state space. You can take control of the pl…

This is the forth entry in my series of Unity for AI Education. Code is available for this and all other projects on my GitHub (username MLivanos), released under an MIT license.  Explore the inner workings of the Q-Learning algorithm for blackjack, a classic casino game where two players receive a hand of two cards and the goal is to get a value of 21 without going over. Aces count as either 1 or…

You Deserve a Seat at the Table provides players with the right tools to excel in corporate environments. This 2D Puzzle game offers an exciting alternative to common dull approaches. Ordinary business concepts such as Critical Thinking and Problem Solving are taught through interactive mini-games. Working your way up the corporate ladder can be tough, but it doesn’t have to be! With You Des…

About Tower Of Hanoi is a mathematical puzzle that involves moving a stack of disks from one peg to another, following certain rules. You can only move one disk at a time, and you can't place a larger disk on top of a smaller one. Your goal is to move the entire tower from the first peg to the middle peg, following the set rules. The Reinforcement Learning Agent If you click the "Agent solve" butt…

Introduction Nim is a strategic game where players take turns removing objects from distinct heaps, aiming to avoid taking the last object. The origins of the game can be traced back to ancient China, and it has been played in various forms for over two thousand years. In this version of Nim, there are three piles, each filled with a random number of tokens. On your turn, you have to remove one or…

About Face off against a reinforcement learning agent in this classic Flash game. Click on your bow and pull back to aim, release to fire. The first to hit their opponent three times wins. The Agent The agent sees its environment through a state, which includes the current wind conditions, the player's position, and the bow's current angle and power. It can choose from five actions: increasing or …

79%Game Brain Score

graphics, story

gameplay, grinding

79% User Score Based on 107 reviews

Might is Right is an old-school turn-based strategy game, it has simple controls and deep complex mechanics.

Welcome! Welcome to my Abstract Painter! It's  an  HTML5 interactive model that allows a user to explore diffusion of color. The interactive simulation is intended to be used by the individual student or learner who is attempting to further understand the concept. The  interactive is a NetLogo simulation built in NetTango which allow a user to manipulate an environment with block-based coding and …

Brief Description: This iteration now includes setting time limits, adjusting target size, dynamic score tracking, and starting the game via a start button. It also retains animation-focused enhancements like choosing which animations to see via a dropdown, adjusting animation speed via slider, reversing animations, allowing for simultaneous animations, and toggling the visibility of UI elements f…

TURN-BASED STRATEGY OF THE NEW GENERATION In this game, strategic decisions are more important than reflexes. You will find exciting single and multiplayer modes, as well as earning levels and rewards. Play in strategic standard mode, quick mode, and also in pairs mode with a friend. The main goal of the game is to stay alive longer than your opponent. A huge list of creatures, heroes, artifacts,…