Games like Nim -Ai

Reinforcement Learning and how it works The tic-tac-toe agent uses reinforcement learning to improve its gameplay. Each turn, it examines the board's state and decides where to place its token (either O or X). It decides where to play its token by looking at a table of values. In the table, each state and possible action (token placement) will have a value ranging from -1 to 1. During play, the ag…

You and the agent alternate turns, clicking to pluck 1, 2, or 3 petals. After your turn, tap the flower's center for the agent's turn. If you click the last petal, you lose. Reinforcement learning and how it works Sunflower is inspired by the classic game of 21. Players count up in increments of 1, 2, or 3, and whoever reaches 21 first loses. You'll face off against a reinforcement learning agent …

You and the agent alternate turns, clicking to pluck 1, 2, or 3 petals. After your turn, tap the flower's center for the agent's turn. If you click the last petal, you lose. Reinforcement learning and how it works Sunflower is inspired by the classic game of 21. Players count up in increments of 1, 2, or 3, and whoever reaches 21 first loses. You'll face off against a reinforcement learning agent …

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 …

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…

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…

Castle Siege – Revised Rules Overview In Castle Siege you act as the commander in charge of besieging four enemy castles. Each castle is defended by one or more cards, and your goal is to capture all the castles by first removing their defenders and then capturing the castle cards themselves. Resource management and tactical play are essential. Difficulty Settings Before setting up t…

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…

In this scenario, the hero (agent) navigates through a grid world with the aim of reaching a chest. The hero is capable of performing four actions: moving up, down, left, or right. Before training the agent, you have the flexibility to modify the map. This is done by left-clicking to position trees and right-clicking to eliminate them. Additionally, the locations of both the hero and the chest can…

"Twilight Struggle" is a strategic board game that simulates the Cold War from the 1950s to the 1990s, where players choose to control either the U.S or U.S.S.R, competing in political influence and coup attempts worldwide. The game's event cards are based on historical events, adding realism and depth to the gameplay. Triggering a nuclear war, however, leads to a sudden end for the players.