Artículos académicos

Esté al día de los artículos académicos más relevantes.

Deep Reinforcement Learning with Double Q-learning

he popular Q-learning algorithm is known to overestimate action values under certain conditions. It was not previously known whether, in practice, such overestimations are common, whether they harm performance, and whether they can generally be prevented. In this paper, we answer all these questions affirmatively. In particular, we first show that the recent DQN algorithm, which combines Q-learning with a deep neural network, suffers from substantial overestimations in some games in the Atari 2600 domain. We then show that the idea behind the Double Q-learning algorithm, which was introduced in a tabular setting, can be generalized to work with large-scale function approximation. We propose a specific adaptation to the DQN algorithm and show that the resulting algorithm not only reduces the observed overestimations, as hypothesized, but that this also leads to much better performance on several games.

Leer artículo

Games, Health and the City: Developing Location-Aware Games for Leveraging the Most Suitable Places for Physical Activity

Location is increasingly gaining strength in the world of games, resulting in a new genre of games called location-aware games. This type of games can be applied to various areas such as medicine, psychology and education, as location and spatial characteristics are horizontal to many application domains. This work tries to increase the number of tools available for psychologists by developing location–aware games for promoting physical activity. It also takes advantage of the urban features that make an area an appropriate place for practice moderate physical activity. The paper presents the methodology followed to identify these healthy urban attributes, describes the technical development of the game and the design of an experiment with real users.

Leer artículo

A Panorama of Artificial and Computational Intelligence in Games

This paper attempts to give a high-level overview of the field of artificial and computational intelligence (AI/CI) in games, with particular reference to how the different core research areas within this field inform and interact with each other, both actually and potentially. We identify ten main research areas within this field: NPC behavior learning, search and planning, player modeling, games as AI benchmarks, procedural content generation, computational narrative, believable agents, AI-assisted game design, general game artificial intelligence and AI in commercial games. We view and analyze the areas from three key perspectives: 1) the dominant AI method(s) used under each area; 2) the relation of each area with respect to the end (human) user; and 3) the placement of each area within a human-computer (player-game) interaction perspective. In addition, for each of these areas we consider how it could inform or interact with each of the other areas; in those cases where we find that meaningful interaction either exists or is possible, we describe the character of that interaction and provide references to published studies, if any. We believe that this paper improves understanding of the current nature of the game AI/CI research field and the interdependences between its core areas by providing a unifying overview. We also believe that the discussion of potential interactions between research areas provides a pointer to many interesting future research projects and unexplored subfields.

Leer artículo

Artículos académicos

Esté al día de los artículos académicos más relevantes.

Deep Reinforcement Learning with Double Q-learning

he popular Q-learning algorithm is known to overestimate action values under certain conditions. It was not previously known whether, in practice, such overestimations are common, whether they harm performance, and whether they can generally be prevented. In this paper, we answer all these questions affirmatively. In particular, we first show that the recent DQN algorithm, which combines Q-learning with a deep neural network, suffers from substantial overestimations in some games in the Atari 2600 domain. We then show that the idea behind the Double Q-learning algorithm, which was introduced in a tabular setting, can be generalized to work with large-scale function approximation. We propose a specific adaptation to the DQN algorithm and show that the resulting algorithm not only reduces the observed overestimations, as hypothesized, but that this also leads to much better performance on several games.

Leer artículo

Games, Health and the City: Developing Location-Aware Games for Leveraging the Most Suitable Places for Physical Activity

Location is increasingly gaining strength in the world of games, resulting in a new genre of games called location-aware games. This type of games can be applied to various areas such as medicine, psychology and education, as location and spatial characteristics are horizontal to many application domains. This work tries to increase the number of tools available for psychologists by developing location–aware games for promoting physical activity. It also takes advantage of the urban features that make an area an appropriate place for practice moderate physical activity. The paper presents the methodology followed to identify these healthy urban attributes, describes the technical development of the game and the design of an experiment with real users.

Leer artículo

A Panorama of Artificial and Computational Intelligence in Games

This paper attempts to give a high-level overview of the field of artificial and computational intelligence (AI/CI) in games, with particular reference to how the different core research areas within this field inform and interact with each other, both actually and potentially. We identify ten main research areas within this field: NPC behavior learning, search and planning, player modeling, games as AI benchmarks, procedural content generation, computational narrative, believable agents, AI-assisted game design, general game artificial intelligence and AI in commercial games. We view and analyze the areas from three key perspectives: 1) the dominant AI method(s) used under each area; 2) the relation of each area with respect to the end (human) user; and 3) the placement of each area within a human-computer (player-game) interaction perspective. In addition, for each of these areas we consider how it could inform or interact with each of the other areas; in those cases where we find that meaningful interaction either exists or is possible, we describe the character of that interaction and provide references to published studies, if any. We believe that this paper improves understanding of the current nature of the game AI/CI research field and the interdependences between its core areas by providing a unifying overview. We also believe that the discussion of potential interactions between research areas provides a pointer to many interesting future research projects and unexplored subfields.

Leer artículo