Página 1 dos resultados de 9 itens digitais encontrados em 0.010 segundos

Galerias e mundos virtuais na educação : aplicação à história da arte

Martins, Maria da Conceição de Magalhães
Fonte: Universidade Aberta de Portugal Publicador: Universidade Aberta de Portugal
Tipo: Dissertação de Mestrado
Publicado em //2012 POR
Relevância na Pesquisa
25.96%
Dissertação de Mestrado em Expressão Gráfica e Audiovisual apresentada à Universidade Aberta; As tecnologias integradas no currículo permitem uma regeneração do ensino e das práticas pedagógicas. Ao utilizar a multimédia no ensino estamos a contribuir para a modernização dos métodos de estudo. Neste projeto ao utilizarem-se aplicações de multimédia específicas foi com o intuito de proporcionar aos alunos situações motivacionais e promotoras de uma aprendizagem significativa dos conteúdos abordados na disciplina de História e Cultura das Artes. É ainda propósito deste projeto estudar e compreender a intercessão das novas tecnologias, sobretudo os ambientes tridimensionais no processo de ensino aprendizagem. Neste sentido, aplicou-se a tecnologia VRML/X3D como apoio à transmissão de conhecimentos na História da Arte. Para tal, criou-se uma aplicação que permitiu fazer o estudo da usabilidade, funcionalidade e acessibilidade deste ambiente 3D no âmbito educativo. Procurou-se com esta investigação, estudar o impacto pedagógico desta aplicação e averiguar se esta facilita a aquisição de conteúdos pedagógicos assim como, desenvolvimento de competência dos alunos, após a sua utilização. O resultado obtido nos exames nacionais constitui-se como indicador positivo a favor da utilização desta aplicação de multimédia...

Reinforcement learning with value advice

Daswani, Mayank; Sunehag, Peter; Hutter, Marcus
Fonte: Journal of Machine Learning Research Publicador: Journal of Machine Learning Research
Tipo: Conference paper
Relevância na Pesquisa
86.36%
The problem we consider in this paper is reinforcement learning with value advice. In this setting, the agent is given limited access to an oracle that can tell it the expected return (value) of any state-action pair with respect to the optimal policy. The agent must use this value to learn an explicit policy that performs well in the environment. We provide an algorithm called RLAdvice, based on the imitation learning algorithm DAgger. We illustrate the effectiveness of this method in the Arcade Learning Environment on three different games, using value estimates from UCT as advice.

Massively Parallel Methods for Deep Reinforcement Learning

Nair, Arun; Srinivasan, Praveen; Blackwell, Sam; Alcicek, Cagdas; Fearon, Rory; De Maria, Alessandro; Panneershelvam, Vedavyas; Suleyman, Mustafa; Beattie, Charles; Petersen, Stig; Legg, Shane; Mnih, Volodymyr; Kavukcuoglu, Koray; Silver, David
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Relevância na Pesquisa
56.05%
We present the first massively distributed architecture for deep reinforcement learning. This architecture uses four main components: parallel actors that generate new behaviour; parallel learners that are trained from stored experience; a distributed neural network to represent the value function or behaviour policy; and a distributed store of experience. We used our architecture to implement the Deep Q-Network algorithm (DQN). Our distributed algorithm was applied to 49 games from Atari 2600 games from the Arcade Learning Environment, using identical hyperparameters. Our performance surpassed non-distributed DQN in 41 of the 49 games and also reduced the wall-time required to achieve these results by an order of magnitude on most games.; Comment: Presented at the Deep Learning Workshop, International Conference on Machine Learning, Lille, France, 2015

The Arcade Learning Environment: An Evaluation Platform for General Agents

Bellemare, Marc G.; Naddaf, Yavar; Veness, Joel; Bowling, Michael
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Relevância na Pesquisa
66.31%
In this article we introduce the Arcade Learning Environment (ALE): both a challenge problem and a platform and methodology for evaluating the development of general, domain-independent AI technology. ALE provides an interface to hundreds of Atari 2600 game environments, each one different, interesting, and designed to be a challenge for human players. ALE presents significant research challenges for reinforcement learning, model learning, model-based planning, imitation learning, transfer learning, and intrinsic motivation. Most importantly, it provides a rigorous testbed for evaluating and comparing approaches to these problems. We illustrate the promise of ALE by developing and benchmarking domain-independent agents designed using well-established AI techniques for both reinforcement learning and planning. In doing so, we also propose an evaluation methodology made possible by ALE, reporting empirical results on over 55 different games. All of the software, including the benchmark agents, is publicly available.

Playing Atari with Deep Reinforcement Learning

Mnih, Volodymyr; Kavukcuoglu, Koray; Silver, David; Graves, Alex; Antonoglou, Ioannis; Wierstra, Daan; Riedmiller, Martin
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 19/12/2013
Relevância na Pesquisa
56.07%
We present the first deep learning model to successfully learn control policies directly from high-dimensional sensory input using reinforcement learning. The model is a convolutional neural network, trained with a variant of Q-learning, whose input is raw pixels and whose output is a value function estimating future rewards. We apply our method to seven Atari 2600 games from the Arcade Learning Environment, with no adjustment of the architecture or learning algorithm. We find that it outperforms all previous approaches on six of the games and surpasses a human expert on three of them.; Comment: NIPS Deep Learning Workshop 2013

Reuse of Neural Modules for General Video Game Playing

Braylan, Alexander; Hollenbeck, Mark; Meyerson, Elliot; Miikkulainen, Risto
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 04/12/2015
Relevância na Pesquisa
35.96%
A general approach to knowledge transfer is introduced in which an agent controlled by a neural network adapts how it reuses existing networks as it learns in a new domain. Networks trained for a new domain can improve their performance by routing activation selectively through previously learned neural structure, regardless of how or for what it was learned. A neuroevolution implementation of this approach is presented with application to high-dimensional sequential decision-making domains. This approach is more general than previous approaches to neural transfer for reinforcement learning. It is domain-agnostic and requires no prior assumptions about the nature of task relatedness or mappings. The method is analyzed in a stochastic version of the Arcade Learning Environment, demonstrating that it improves performance in some of the more complex Atari 2600 games, and that the success of transfer can be predicted based on a high-level characterization of game dynamics.; Comment: Accepted at AAAI 16

State of the Art Control of Atari Games Using Shallow Reinforcement Learning

Liang, Yitao; Machado, Marlos C.; Talvitie, Erik; Bowling, Michael
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 04/12/2015
Relevância na Pesquisa
56.04%
The recently introduced Deep Q-Networks (DQN) algorithm has gained attention as one of the first successful combinations of deep neural networks and reinforcement learning. Its promise was demonstrated in the Arcade Learning Environment (ALE), a challenging framework composed of dozens of Atari 2600 games used to evaluate general competency in AI. It achieved dramatically better results than earlier approaches, showing that its ability to learn good representations is quite robust and general. This paper attempts to understand the principles that underly DQN's impressive performance and to better contextualize its success. We systematically evaluate the importance of key representational biases encoded by DQN's network by proposing simple linear representations that make use of these concepts. Incorporating these characteristics, we obtain a computationally practical feature set that achieves competitive performance to DQN in the ALE. Besides offering insight into the strengths and weaknesses of DQN, we provide a generic representation for the ALE, significantly reducing the burden of learning a representation for each game. Moreover, we also provide a simple, reproducible benchmark for the sake of comparison to future work in the ALE.

A Comparison of learning algorithms on the Arcade Learning Environment

Defazio, Aaron; Graepel, Thore
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 30/10/2014
Relevância na Pesquisa
76.44%
Reinforcement learning agents have traditionally been evaluated on small toy problems. With advances in computing power and the advent of the Arcade Learning Environment, it is now possible to evaluate algorithms on diverse and difficult problems within a consistent framework. We discuss some challenges posed by the arcade learning environment which do not manifest in simpler environments. We then provide a comparison of model-free, linear learning algorithms on this challenging problem set.

True Online Temporal-Difference Learning

van Seijen, Harm; Mahmood, A. Rupam; Pilarski, Patrick M.; Machado, Marlos C.; Sutton, Richard S.
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 13/12/2015
Relevância na Pesquisa
56.04%
The temporal-difference methods TD($\lambda$) and Sarsa($\lambda$) form a core part of modern reinforcement learning. Their appeal comes from their good performance, low computational cost, and their simple interpretation, given by their forward view. Recently, new versions of these methods were introduced, called true online TD($\lambda$) and true online Sarsa($\lambda$), respectively (van Seijen and Sutton, 2014). Algorithmically, these true online methods only make two small changes to the update rules of the regular methods, and the extra computational cost is negligible in most cases. However, they follow the ideas underlying the forward view much more closely. In particular, they maintain an exact equivalence with the forward view at all times, whereas the traditional versions only approximate it for small step-sizes. We hypothesize that these true online methods not only have better theoretical properties, but also dominate the regular methods empirically. In this article, we put this hypothesis to the test by performing an extensive empirical comparison. Specifically, we compare the performance of true online TD($\lambda$)/Sarsa($\lambda$) with regular TD($\lambda$)/Sarsa($\lambda$) on random MRPs, a real-world myoelectric prosthetic arm...