Georgios N. Yannakakis Julian Togelius Page 1 Artificial Intelligence and Games Georgios N.
Yannakakis Julian Togelius Page 2 Artificial Intelligence and Games Page 3 Georgios N …

Data aggregation techniques can significantly improve vision-based policy learning within a
training environment, eg, learning to drive in a specific simulation condition. However, as on …

Recent progress in Reinforcement Learning (RL), fueled by its combination, with Deep
Learning has enabled impressive results in learning to interact with complex virtual …

This thesis investigates ways to extend the use of Reinforcement Learning (RL) to Behavior
Trees (BTs). BTs are used in the field of Artificial Intelligence (AI) in order to create modular …

Imitation learning has shown promise for autonomous driving, but suffers from covariate
shift, where the policy performs poorly in unseen environments. DAgger is a popular …

Deep Reinforcement Learning has enabled the control of increasingly complex and high-
dimensional problems. However, the need of vast amounts of data before reasonable …

Imitating an expert policy is one way to boost reinforcement learning algorithms which, in
most cases, rely on random exploration and a huge amount of data. While some major …

This thesis proposes methods for performing autonomous navigation with a topological map
and a vision sensor in a parking lot. These methods are necessary to complete fully …

Abstract The International Conference on Autonomous Agents and Multiagent Systems
(AAMAS) brings together researchers in all areas of agent technology, and provides a single …

A criação de agentes inteligentes é uma área da inteligência artificial que busca, dentre
outros objetivos, construir entidades capazes de desempenhar ações semelhantes às de …