In modern racing games programming non-player characters with believable and sophisticated behaviors is getting increasingly challenging. Recently, several works in the literature ...
Bayesian inference is an appealing approach for leveraging prior knowledge in reinforcement learning (RL). In this paper we describe an algorithm for discovering different classes...
We describe a generalized Q-learning type algorithm for reinforcement learning in competitive multi-agent games. We make the observation that in a competitive setting with adaptive...
Pieter Jan't Hoen, Sander M. Bohte, Han La Poutr&e...
Research in learning and planning in real-time strategy (RTS) games is very interesting in several industries such as military industry, robotics, and most importantly game industr...
Ibrahim Fathy, Mostafa Aref, Omar Enayet, Abdelrah...
Although TD-Gammon is one of the major successes in machine learning, it has not led to similar impressive breakthroughs in temporal difference learning for other applications or ...