Package provides java implementation of reinforcement learning algorithms such Q-Learn, R-Learn, SARSA, Actor-Critic

Demo of java-reinforcement-learning library using flappy bird

CS7641 - Machine Learning - Assignment 4 - Markov Decision Processes

An application for "evolving" near-optimal offensive play calling strategies.

Demo of reinforcement learning using tic-tac-toe

Genetic Based Selection Forced Reinforcement Learning

Flappy Bird for artificial intelligence/machine learning (Agent available: Q-Learning, SARSA, and combined with Backpropagation)

Apply value iteration, policy iteration and Q learning to develop policies for agents to reach goal state.

Applying Markov Decision Processes and Q-Learning to a robot movement model

Uses Markov decision processes (MDPs) and Temporal Difference (TD) Q-learning to maximize reward in a "grid world".

This project is a Java implementation of a Genetic Algorithm, a stochastic optimization algorithm inspired by natural selection and genetics.

An implementation of Reinforcement Learning using the Q-Learning algorithm and Function Approximation with Backpropagation Neural Network.

通过Q-learning与Minmax-pruning对比实现的5*5围棋AI

From 2008: Reinforcement Learning (Q-Learning) and playing a game of Othello. Also, Greedy Player, Random Player, and Human Player. This is grad school. More fun times.

Classic Snake game in Java and Processing 3, with Q-Learning.

Package provides java implementation of the ART-based ANN FALCON

Basic q-learning algorithm for navigating through a maze. The agent has no prior knowledge of danger (red blocks) or the objective location (yellow block), it learns exclusively through experiencing the ramifications of its actions.

Using reinforcement learning techniques, robot battle tanks were taught how to fight in a tank battle

Q Learning EV3 Robot Learning How to Walk

Atividade de IA, usando o algoritmo Q-Learning.