Limpar
141 resultados

Acesso aberto

Tipo do recurso

Ano de criação

Produção nacional

Revisado por pares

Áreas

Idioma

Editores

Artigo Acesso aberto

Marc G. Bellemare, Joel Veness, Michael Bowling,

... awareness in reinforcement learning using the platform of Atari 2600 games. We introduce a technique for accurately identifying ... 46 unseen, diverse, and challenging games for the Atari 2600 console. Our results suggest that contingency awareness is ...

Tópico(s): Artificial Intelligence in Games

2021 - Association for the Advancement of Artificial Intelligence | Proceedings of the AAAI Conference on Artificial Intelligence

Capítulo de livro Acesso aberto Revisado por pares

Per‐Arne Andersen, Morten Goodwin, Ole‐Christoffer Granmo,

... however, these are either overly simplistic such as Atari 2600 or complex such as Starcraft II from Blizzard Entertainment. We propose a game environment in between Atari 2600 and Starcraft II, particularly targeting Deep Reinforcement Learning ...

Tópico(s): Game Theory and Applications

2017 - Springer Science+Business Media | Lecture notes in computer science

Artigo Acesso aberto Revisado por pares

Abdul Mueed Hafiz, M. Hassaballah, Abdullah Alqahtani, Shtwai Alsubai, Mohamed Abdel Hameed,

... proposed ensemble approach on OpenAI Gym tasks, and Atari 2600 games as compared to recent techniques. The proposed ... the-art results on four out of five Atari 2600 games.

Tópico(s): Neural Networks and Reservoir Computing

2023 - | Computer Systems Science and Engineering

Artigo Acesso aberto Revisado por pares

Kazuteru Miyazaki,

... Q-learning has produced excellent results for several Atari 2600 games. In this paper, we propose an exploitation- ... This method is compared with a DQN in Atari 2600 games. We demonstrate that the proposed DQNwithPS method ...

Tópico(s): Digital Games and Media

2017 - Fuji Technology Press Ltd. | Journal of Advanced Computational Intelligence and Intelligent Informatics

Capítulo de livro Revisado por pares

Jianwei Zhai, Quan Liu, Zongzhang Zhang, Shan Zhong, Haijun Zhu, Peng Zhang, Cijia Sun,

... solving problems approaching real-world complexities such as Atari 2600 games. To remove temporal correlation between the observed ... both average score and learning rate on four Atari 2600 games.

Tópico(s): Evolutionary Algorithms and Applications

2016 - Springer Science+Business Media | Lecture notes in computer science

Artigo Acesso aberto Revisado por pares

Stefan Elfwing, Eiji Uchibe, Kenji Doya,

... algorithm DQN achieved human-level performance in many Atari 2600 games. The purpose of this study is twofold. ... agents, and, then, by outperforming DQN in the Atari 2600 domain by using a deep Sarsa(λ) agent ...

Tópico(s): Adaptive Dynamic Programming Control

2018 - Elsevier BV | Neural Networks

Artigo Acesso aberto Revisado por pares

Kazuteru Miyazaki,

... Q-learning have demonstrated excellent results for several Atari 2600 games. In this paper, we propose an exploitation- ... is compared to a DQN in Pong of Atari 2600 games. We demonstrate that the proposed DQNwithPS method ...

Tópico(s): Artificial Intelligence in Games

2018 - Elsevier BV | Procedia Computer Science

Capítulo de livro Revisado por pares

Jakub Sygnowski, Henryk Michalewski,

... in the memory of a video game console Atari 2600. We consider four models of neural networks which ...

Tópico(s): Artificial Intelligence in Games

2017 - Springer Science+Business Media | Communications in computer and information science

Artigo Acesso aberto

Son Pham, Keyi Zhang, Tung Phan, Jasper Ding, Christopher L. Dancy,

... develop reinforcement learning (RL) algorithms to play various Atari 2600 games, resulting in new applications of algorithms such ... Entertainment System (SNES) are far more complicated than Atari 2600 games as many of these state-of-the- ...

Tópico(s): Reinforcement Learning in Robotics

2018 - Association for the Advancement of Artificial Intelligence | Proceedings of the AAAI Conference on Artificial Intelligence

Artigo Acesso aberto Revisado por pares

Jason Thompson, Ken S. McAllister, Judd Ethan Ruggill,

... garde and vice-versa. Consider, for example, the Atari 2600 paddle. Compared to a PlayStation 3 controller, with ... PlayStation 3) supersedes an older one (e.g., Atari 2600), the older one will often sit like a ...

Tópico(s): Artificial Intelligence in Games

2009 - Queensland University of Technology | M/C Journal

Artigo Acesso aberto

Matthew Hausknecht, Joel Lehman, Risto Miikkulainen, Peter Stone,

... Specifically, it introduces a neuroevolution approach to general Atari 2600 game playing. Four neuroevolution algorithms were paired with three different state representations and evaluated on a set of 61 Atari games. The neuroevolution agents represent different points along ...

Tópico(s): Reinforcement Learning in Robotics

2014 - Institute of Electrical and Electronics Engineers | IEEE Transactions on Computational Intelligence and AI in Games

Capítulo de livro Revisado por pares

Stephen Kelly, Malcolm I. Heywood,

... games from the Arcade Learning Environment (ALE), an Atari 2600 video game emulator. The games considered here correspond to those in which deep learning was unable to reach a threshold of play consistent with that of a human. Information provided to the learning agent is limited to that which a human would experience. That is, screen capture sensory input, Atari joystick actions, and game score. The performance of ...

Tópico(s): Evolution and Genetic Dynamics

2017 - Springer Science+Business Media | Lecture notes in computer science

Artigo Acesso aberto Revisado por pares

Marc G. Bellemare, Yavar Naddaf, Joel Veness, Michael Bowling,

... technology. ALE provides an interface to hundreds of Atari 2600 game environments, each one different, interesting, and designed ...

Tópico(s): Evolutionary Algorithms and Applications

2013 - AI Access Foundation | Journal of Artificial Intelligence Research

Artigo Acesso aberto

Haiyan Yin, Sinno Jialin Pan,

... network while guaranteeing a good performance. We use Atari 2600 games as testing environment to demonstrate the efficiency ...

Tópico(s): Neural dynamics and brain function

2017 - Association for the Advancement of Artificial Intelligence | Proceedings of the AAAI Conference on Artificial Intelligence

Artigo Acesso aberto Revisado por pares

Eiji Uchibe,

... reinforcement learning is applied into two benchmark games: Atari 2600 and Reversi. Simulation results show that our method ...

Tópico(s): Adaptive Dynamic Programming Control

2017 - Springer Science+Business Media | Neural Processing Letters

Artigo Acesso aberto

Aravind S. Lakshminarayanan, Sahil Sharma, Balaraman Ravindran,

... the performance on relatively harder games in the Atari 2600 domain, independent of the underlying Deep Reinforcement Learning ...

Tópico(s): Explainable Artificial Intelligence (XAI)

2017 - Association for the Advancement of Artificial Intelligence | Proceedings of the AAAI Conference on Artificial Intelligence

Capítulo de livro Acesso aberto Revisado por pares

Mark McKenzie, Peter Loxley, William Billingsley, Sebastien Wong,

... to outperform human players for a number of Atari 2600 games. The key findings of this paper is ...

Tópico(s): Artificial Intelligence in Games

2017 - Springer Science+Business Media | Lecture notes in computer science

Artigo Acesso aberto

Yuu Jinnai, Alex Fukunaga,

... search in domain-independent black-box planning for Atari 2600 games in the Arcade Learning Environment (ALE), adding ...

Tópico(s): Machine Learning and Algorithms

2017 - Association for the Advancement of Artificial Intelligence | Proceedings of the AAAI Conference on Artificial Intelligence

Artigo Revisado por pares

Junpeng Wang, Liang Gou, Han‐Wei Shen, Hao Yang,

... ability to surpass professional human players across many Atari 2600 games. Despite the superhuman performance, in-depth understanding ...

Tópico(s): Explainable Artificial Intelligence (XAI)

2018 - Institute of Electrical and Electronics Engineers | IEEE Transactions on Visualization and Computer Graphics

Artigo Acesso aberto

Wilmer Bandres, Blai Bonet, Héctor Geffner,

... yield state-of-the-art results in the Atari 2600 video games. For this, the states were associated ...

Tópico(s): Reinforcement Learning in Robotics

2018 - Association for the Advancement of Artificial Intelligence | Proceedings of the AAAI Conference on Artificial Intelligence

Artigo Acesso aberto Revisado por pares

Marlos C. Machado, Marc G. Bellemare, Erik Talvitie, Joel Veness, Matthew Hausknecht, Michael Bowling,

... AI agents with general competency across dozens of Atari 2600 games. It supports a variety of different problem ...

Tópico(s): Advanced Bandit Algorithms Research

2018 - AI Access Foundation | Journal of Artificial Intelligence Research

Artigo Revisado por pares

Cindy Orosy-Fildes, Robert W. Allan,

... a 15-min. practice treatment interval on an Atari 2600 videogame system between the two test sessions. Analysis ...

Tópico(s): Educational Games and Gamification

1989 - SAGE Publishing | Perceptual and Motor Skills

Artigo

Lee Allen,

... the kids with such popular consoles as the Atari 2600. There was no Internet as we know it, ...

Tópico(s): Technology and Security Systems

2008 - SAGE Publishing | Phi Delta Kappan

Artigo Revisado por pares

Matthew Thomas Payne, Peter Alilunas,

... oriented 8-bit video games produced for the Atari 2600 home game console, this essay argues that the ...

Tópico(s): Sexuality, Behavior, and Technology

2015 - SAGE Publishing | Television & New Media

Artigo Acesso aberto

Alexander Braylan, Mark Hollenbeck, Elliot Meyerson, Risto Miikkulainen,

... improves performance in some of the more complex Atari 2600 games, and that the success of transfer can ...

Tópico(s): Artificial Intelligence in Games

2016 - Association for the Advancement of Artificial Intelligence | Proceedings of the AAAI Conference on Artificial Intelligence

Artigo Acesso aberto

Marc G. Bellemare, Georg Ostrovski, Arthur Guez, Philip S. Thomas, Rémi Munos,

... We conclude with an empirical study on 60 Atari 2600 games illustrating the strong potential of these new ...

Tópico(s): Advanced Bandit Algorithms Research

2016 - Association for the Advancement of Artificial Intelligence | Proceedings of the AAAI Conference on Artificial Intelligence

Artigo Acesso aberto

Hado van Hasselt, Arthur Guez, David Silver,

... from substantial overestimations in some games in the Atari 2600 domain. We then show that the idea behind ...

Tópico(s): Reinforcement Learning in Robotics

2016 - Association for the Advancement of Artificial Intelligence | Proceedings of the AAAI Conference on Artificial Intelligence

Artigo Acesso aberto

Matteo Hessel, Joseph Modayil, Hado van Hasselt, Tom Schaul, Georg Ostrovski, Will Dabney, Dan Horgan, Bilal Piot, Mohammad Gheshlaghi Azar, David Silver,

... provides state-of-the-art performance on the Atari 2600 benchmark, both in terms of data efficiency and ...

Tópico(s): Modular Robots and Swarm Intelligence

2018 - Association for the Advancement of Artificial Intelligence | Proceedings of the AAAI Conference on Artificial Intelligence

Artigo Acesso aberto

Will Dabney, Mark Rowland, Marc G. Bellemare, Rémi Munos,

... Finally, we evaluate this new algorithm on the Atari 2600 games, observing that it significantly outperforms many of ...

Tópico(s): Evolutionary Algorithms and Applications

2018 - Association for the Advancement of Artificial Intelligence | Proceedings of the AAAI Conference on Artificial Intelligence