检索结果-内蒙古大学图书馆

Biasing MCTS with features for general games

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Soemers, Dennis J.N.J. Piette, Éric Browne, Cameron Department of Data Science and Knowledge Engineering Maastricht University Maastricht Netherlands

This paper proposes using a linear function approximator, rather than a deep neural network (DNN), to bias a Monte Carlo tree search (MCTS) player for general games. This is unlikely to match the potential raw playing strength of DNNs, but has advantages in terms of generality, interpretability and resources (time and hardware) required for training. Features describing local patterns are used as inputs. The features are formulated in such a way that they are easily interpretable and applicable to a wide range of general games, and might encode simple local strategies. We gradually create new features during the same self-play training process used to learn feature weights. We evaluate the playing strength of an MCTS player biased by learnt features against a standard upper confidence bounds for trees (UCT) player in multiple different board games, and demonstrate significantly improved playing strength in the majority of them after a small number of self-play training games. Copyright © 2019, The Authors. All rights reserved.

关键词： Deep neural networks

Ludii as a competition platform

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Stephenson, Matthew Piette, Éric Soemers, Dennis J.N.J. Browne, Cameron Department of Data Science and Knowledge Engineering Maastricht University Maastricht Netherlands

Ludii is a general game system being developed as part of the ERC-funded Digital Ludeme Project (DLP). While its primary aim is to model, play, and analyse the full range of traditional strategy games, Ludii also has the potential to support a wide range of AI research topics and competitions. This paper describes some of the future competitions and challenges that we intend to run using the Ludii system, highlighting some of its most important aspects that can potentially lead to many algorithm improvements and new avenues of research. We compare and contrast our proposed competition motivations, goals and frameworks against those of existing general game playing competitions, addressing the strengths and weaknesses of each platform. Copyright © 2019, The Authors. All rights reserved.

关键词：

Query Minimization Under Stochastic Uncertainty 14th

学校读者我要写书评

暂无评论

Query Minimization Under Stochastic Uncertainty

14th Latin American Symposium on Theoretical Informatics, LATIN 2020

作者： Chaplick, Steven Halldórsson, Magnús M. de Lima, Murilo S. Tonoyan, Tigran Lehrstuhl für Informatik I Universität Würzburg Würzburg Germany Department of Data Science and Knowledge Engineering Maastricht University Maastricht Netherlands ICE-TCS Department of Computer Science Reykjavik University Reykjavik Iceland School of Informatics University of Leicester Leicester United Kingdom Computer Science Department Technion Institute of Technology Haifa Israel

ISBN: (纸本)9783030617912

We study problems with stochastic uncertainty data on intervals for which the precise value can be queried by paying a cost. The goal is to devise an adaptive decision tree to find a correct solution to the problem in consideration while minimizing the expected total query cost. We show that sorting in this scenario can be performed in polynomial time, while finding the data item with minimum value seems to be hard. This contradicts intuition, since the minimum problem is easier both in the online setting with adversarial inputs and in the offline verification setting. However, the stochastic assumption can be leveraged to beat both deterministic and randomized approximation lower bounds for the online setting. Although some literature has been devoted to minimizing query/probing costs when solving uncertainty problems with stochastic input, none of them have considered the setting we describe. Our approach is closer to the study of query-competitive algorithms, and it gives a better perspective on the impact of the stochastic assumption. © 2020, Springer Nature Switzerland AG.

关键词： Sorting

LoGANv2: Conditional Style-Based Logo Generation with Generative Adversarial Networks

学校读者我要写书评

暂无评论

LoGANv2: Conditional Style-Based Logo Generation with Genera...

International Conference on Machine Learning and Applications (ICMLA)

作者： Cedric Oeldorf Gerasimos Spanakis Department of Data Science and Knowledge Engineering Maastricht University Maastricht The Netherlands

Domains such as logo synthesis, in which the data has a high degree of multi-modality, still pose a challenge for generative adversarial networks (GANs). Recent research shows that progressive training (ProGAN) and mapping network extensions (StyleGAN) enable both increased training stability for higher dimensional problems and better feature separation within the embedded latent space. However, these architectures leave limited control over shaping the output of the network. This paper explores a conditional extension to the StyleGAN architecture with the aim of firstly, improving on the low resolution results of previous research and, secondly, increasing the controllability of the output through the use of synthetic class-conditions. Furthermore, methods of extracting such class conditions are explored, where the challenge lies in the fact that, visual logo characteristics are hard to define. The introduced conditional style-based generator architecture is trained on the extracted class-conditions in two experiments and studied relative to the performance of an unconditional model. Results show that, whilst the unconditional model more closely matches the training distribution, high quality conditions enabled the embedding of finer details onto the latent space, leading to more diverse output.

关键词： Training Gallium nitride Generators Image resolution Aerospace electronics Visualization Mathematical model

Feature re-learning with data augmentation for video relevance prediction

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Dong, Jianfeng Wang, Xun Zhang, Leimin Xu, Chaoxi Yang, Gang Li, Xirong College of Computer and Information Engineering Zhejiang Gongshang University Hangzhou310035 China Key Lab of Data Engineering and Knowledge Engineering Renmin University of China AI & Media Computing Lab School of Information Renmin University of China Beijing100872 China

Predicting the relevance between two given videos with respect to their visual content is a key component for content-based video recommendation and retrieval. Thanks to the increasing availability of pre-trained image and video convolutional neural network models, deep visual features are widely used for video content representation. However, as how two videos are relevant is task-dependent, such off-the-shelf features are not always optimal for all tasks. Moreover, due to varied concerns including copyright, privacy and security, one might have access to only pre-computed video features rather than original videos. We propose in this paper feature re-learning for improving video relevance prediction, with no need of revisiting the original video content. In particular, re-learning is realized by projecting a given deep feature into a new space by an affine transformation. We optimize the re-learning process by a novel negative-enhanced triplet ranking loss. In order to generate more training data, we propose a new data augmentation strategy which works directly on frame-level and video-level features. Extensive experiments in the context of the Hulu Content-based Video Relevance Prediction Challenge 2018 justify the effectiveness of the proposed method and its state-of-the-art performance for content-based video relevance prediction. Copyright © 2020, The Authors. All rights reserved.

关键词： Convolutional neural networks

An overview of the ludii general game system

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Stephenson, Matthew Piette, Éric Soemers, Dennis J.N.J. Browne, Cameron Department of Data Science and Knowledge Engineering Maastricht University Maastricht Netherlands

The Digital Ludeme Project (DLP) aims to reconstruct and analyse over 1000 traditional strategy games using modern techniques. One of the key aspects of this project is the development of Ludii, a general game system that will be able to model and play the complete range of games required by this project. Such an undertaking will create a wide range of possibilities for new AI challenges. In this paper we describe many of the features of Ludii that can be used. This includes designing and modifying games using the Ludii game description language, creating agents capable of playing these games, and several advantages the system has over prior general game software. Copyright © 2019, The Authors. All rights reserved.

关键词： Software agents

An empirical evaluation of two general game systems: Ludii and RBG

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Piette, Éric Stephenson, Matthew Soemers, Dennis J.N.J. Browne, Cameron Department of Data Science and Knowledge Engineering Maastricht University Maastricht Netherlands

Although General Game Playing (GGP) systems can facilitate useful research in Artificial Intelligence (AI) for game-playing, they are often computationally inefficient and somewhat specialised to a specific class of games. However, since the start of this year, two General Game Systems have emerged that provide efficient alternatives to the academic state of the art - the Game Description Language (GDL). In order of publication, these are the Regular Boardgames language (RBG), and the Ludii system. This paper offers an experimental evaluation of Ludii. Here, we focus mainly on a comparison between the two new systems in terms of two key properties for any GGP system: simplicity/clarity (e.g. human-readability), and efficiency. Copyright © 2019, The Authors. All rights reserved.

关键词： knowledge representation

LoGANv2: Conditional Style-Based Logo Generation with Generative Adversarial Networks

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Oeldorf, Cedric Spanakis, Gerasimos Department of Data Science and Knowledge Engineering Maastricht University Maastricht Netherlands

—Domains such as logo synthesis, in which the data has a high degree of multi-modality, still pose a challenge for generative adversarial networks (GANs). Recent research shows that progressive training (ProGAN) and mapping network extensions (StyleGAN) enable both increased training stability for higher dimensional problems and better feature separation within the embedded latent space. However, these architectures leave limited control over shaping the output of the network, which is an undesirable trait in the case of logo synthesis. This paper explores a conditional extension to the StyleGAN architecture with the aim of firstly, improving on the low resolution results of previous research and, secondly, increasing the controllability of the output through the use of synthetic class-conditions. Furthermore, methods of extracting such class conditions are explored with a focus on the human interpretability, where the challenge lies in the fact that, by nature, visual logo characteristics are hard to define. The introduced conditional style-based generator architecture is trained on the extracted class-conditions in two experiments and studied relative to the performance of an unconditional model. Results show that, whilst the unconditional model more closely matches the training distribution, high quality conditions enabled the embedding of finer details onto the latent space, leading to more diverse output. Copyright © 2019, The Authors. All rights reserved.

关键词： Generative adversarial networks

Learning policies from self-play with policy gradients and MCTS value estimates

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Soemers, Dennis J.N.J. Piette, Éric Stephenson, Matthew Browne, Cameron Department of Data Science and Knowledge Engineering Maastricht University Maastricht Netherlands

In recent years, state-of-the-art game-playing agents often involve policies that are trained in self-playing processes where Monte Carlo tree search (MCTS) algorithms and trained policies iteratively improve each other. The strongest results have been obtained when policies are trained to mimic the search behaviour of MCTS by minimising a cross-entropy loss. Because MCTS, by design, includes an element of exploration, policies trained in this manner are also likely to exhibit a similar extent of exploration. In this paper, we are interested in learning policies for a project with future goals including the extraction of interpretable strategies, rather than state-of-the-art game-playing performance. For these goals, we argue that such an extent of exploration is undesirable, and we propose a novel objective function for training policies that are not exploratory. We derive a policy gradient expression for maximising this objective function, which can be estimated using MCTS value estimates, rather than MCTS visit counts. We empirically evaluate various properties of resulting policies, in a variety of board games. Copyright © 2019, The Authors. All rights reserved.

关键词： Reinforcement learning