In this work we investigate whether it is plausible to use the performance of a reinforcement learning (RL) agent to estimate the difficulty measured as the player completion rate of different levels in the mobile puzzle game Lily's Garden.For this purpose we train an RL agent and measure the number of moves required to complete a level. This is then compared to the level completion rate of a large sample of real players.We find that the strongest predictor of player completion rate for a level is the number of moves taken to complete a level of the ~5% best runs of the agent on a given level. A very interesting observation is that, while in absolute terms, the agent is unable to reach human-level performance across all levels, the differences in terms of behaviour between levels are highly correlated to the differences in human behaviour. Thus, despite performing sub-par, it is still possible to use the performance of the agent to estimate, and perhaps further model, player metrics.
相關內容
We propose an end-to-end Automatic Speech Recognition (ASR) system that can be trained on transcribed speech data, text-only data, or a mixture of both. The proposed model uses an integrated auxiliary block for text-based training. This block combines a non-autoregressive multi-speaker text-to-mel-spectrogram generator with a GAN-based enhancer to improve the spectrogram quality. The proposed system can generate a mel-spectrogram dynamically during training. It can be used to adapt the ASR model to a new domain by using text-only data from this domain. We demonstrate that the proposed training method significantly improves ASR accuracy compared to the system trained on transcribed speech only. It also surpasses cascade TTS systems with the vocoder in the adaptation quality and training speed.
We present the results of a study done in order to validate concepts and methods that have been introduced in (Johansen and Fischer-Hubner, 2020. "Making GDPR Usable: A Model to Support Usability Evaluations of Privacy." in IFIP AICT 576, 275-291). We use as respondents in our interviews experts working across fields of relevance to these concepts, including law and data protection/privacy, certifications and standardization, and usability (as studied in the field of Human-Computer Interaction). We study the experts' opinions about four new concepts, namely: (i) a definition of Usable Privacy, (ii) 30 Usable Privacy Goals identified as excerpts from the GDPR (European General Data Protection Regulation), (iii) a set of 25 corresponding Usable Privacy Criteria together with their multiple measurable sub-criteria, and (iv) the Usable Privacy Cube model, which puts all these together with the EuroPriSe certification criteria, with the purpose of making explicit several aspects of certification processes such as orderings of criteria, interactions between these, different stakeholder perspectives, and context of use/processing. The expert opinions are varied, example-rich, and forward-looking, which gives a impressive list of open problems where the above four concepts can work as a foundation for further developments. We employed a critical qualitative research, using theory triangulation to analyze the data representing three groups of experts, categorized as 'certifications', 'law', and 'usability', coming both from industry and academia. The results of our analysis show agreement among the experts about the need for evaluations and measuring of usability of privacy in order to allow for exercising data subjects' rights and to evaluate the degree to which data controllers comply with the data protection principles.
Matching is a popular nonparametric covariate adjustment strategy in empirical health services research. Matching helps construct two groups comparable in many baseline covariates but different in some key aspects under investigation. In health disparities research, it is desirable to understand the contributions of various modifiable factors, like income and insurance type, to the observed disparity in access to health services between different groups. To single out the contributions from the factors of interest, we propose a statistical matching methodology that constructs nested matched comparison groups from, for instance, White men, that resemble the target group, for instance, black men, in some selected covariates while remaining identical to the white men population before matching in the remaining covariates. Using the proposed method, we investigated the disparity gaps between white men and black men in the US in prostate-specific antigen (PSA) screening based on the 2020 Behavioral Risk Factor Surveillance System (BFRSS) database. We found a widening PSA screening rate as the white matched comparison group increasingly resembles the black men group and quantified the contribution of modifiable factors like socioeconomic status. Finally, we provide code that replicates the case study and a tutorial that enables users to design customized matched comparison groups satisfying multiple criteria.
In this work, we present a novel method for hierarchically variable clustering using singular value decomposition. Our proposed approach provides a non-parametric solution to identify block diagonal patterns in covariance (correlation) matrices, thereby grouping variables according to their dissimilarity. We explain the methodology and outline the incorporation of linkage functions to assess dissimilarities between clusters. To validate the efficiency of our method, we perform both a simulation study and an analysis of real-world data. Our findings show the approach's robustness. We conclude by discussing potential extensions and future directions for research in this field. Supplementary materials for this article can be accessed online.
Efficient shape-constrained inference for the autocovariance sequence from a reversible Markov chain
In this paper, we study the problem of estimating the autocovariance sequence resulting from a reversible Markov chain. A motivating application for studying this problem is the estimation of the asymptotic variance in central limit theorems for Markov chains. We propose a novel shape-constrained estimator of the autocovariance sequence, which is based on the key observation that the representability of the autocovariance sequence as a moment sequence imposes certain shape constraints. We examine the theoretical properties of the proposed estimator and provide strong consistency guarantees for our estimator. In particular, for geometrically ergodic reversible Markov chains, we show that our estimator is strongly consistent for the true autocovariance sequence with respect to an $\ell_2$ distance, and that our estimator leads to strongly consistent estimates of the asymptotic variance. Finally, we perform empirical studies to illustrate the theoretical properties of the proposed estimator as well as to demonstrate the effectiveness of our estimator in comparison with other current state-of-the-art methods for Markov chain Monte Carlo variance estimation, including batch means, spectral variance estimators, and the initial convex sequence estimator.
Many models of learning in teams assume that team members can share solutions or learn concurrently. However, these assumptions break down in multidisciplinary teams where team members often complete distinct, interrelated pieces of larger tasks. Such contexts make it difficult for individuals to separate the performance effects of their own actions from the actions of interacting neighbors. In this work, we show that individuals can overcome this challenge by learning from network neighbors through mediating artifacts (like collective performance assessments). When neighbors' actions influence collective outcomes, teams with different networks perform relatively similarly to one another. However, varying a team's network can affect performance on tasks that weight individuals' contributions by network properties. Consequently, when individuals innovate (through ``exploring'' searches), dense networks hurt performance slightly by increasing uncertainty. In contrast, dense networks moderately help performance when individuals refine their work (through ``exploiting'' searches) by efficiently finding local optima. We also find that decentralization improves team performance across a battery of 34 tasks. Our results offer design principles for multidisciplinary teams within which other forms of learning prove more difficult.
Graph-centric artificial intelligence (graph AI) has achieved remarkable success in modeling interacting systems prevalent in nature, from dynamical systems in biology to particle physics. The increasing heterogeneity of data calls for graph neural architectures that can combine multiple inductive biases. However, combining data from various sources is challenging because appropriate inductive bias may vary by data modality. Multimodal learning methods fuse multiple data modalities while leveraging cross-modal dependencies to address this challenge. Here, we survey 140 studies in graph-centric AI and realize that diverse data types are increasingly brought together using graphs and fed into sophisticated multimodal models. These models stratify into image-, language-, and knowledge-grounded multimodal learning. We put forward an algorithmic blueprint for multimodal graph learning based on this categorization. The blueprint serves as a way to group state-of-the-art architectures that treat multimodal data by choosing appropriately four different components. This effort can pave the way for standardizing the design of sophisticated multimodal architectures for highly complex real-world problems.
In large-scale systems there are fundamental challenges when centralised techniques are used for task allocation. The number of interactions is limited by resource constraints such as on computation, storage, and network communication. We can increase scalability by implementing the system as a distributed task-allocation system, sharing tasks across many agents. However, this also increases the resource cost of communications and synchronisation, and is difficult to scale. In this paper we present four algorithms to solve these problems. The combination of these algorithms enable each agent to improve their task allocation strategy through reinforcement learning, while changing how much they explore the system in response to how optimal they believe their current strategy is, given their past experience. We focus on distributed agent systems where the agents' behaviours are constrained by resource usage limits, limiting agents to local rather than system-wide knowledge. We evaluate these algorithms in a simulated environment where agents are given a task composed of multiple subtasks that must be allocated to other agents with differing capabilities, to then carry out those tasks. We also simulate real-life system effects such as networking instability. Our solution is shown to solve the task allocation problem to 6.7% of the theoretical optimal within the system configurations considered. It provides 5x better performance recovery over no-knowledge retention approaches when system connectivity is impacted, and is tested against systems up to 100 agents with less than a 9% impact on the algorithms' performance.
In the past few years, the emergence of pre-training models has brought uni-modal fields such as computer vision (CV) and natural language processing (NLP) to a new era. Substantial works have shown they are beneficial for downstream uni-modal tasks and avoid training a new model from scratch. So can such pre-trained models be applied to multi-modal tasks? Researchers have explored this problem and made significant progress. This paper surveys recent advances and new frontiers in vision-language pre-training (VLP), including image-text and video-text pre-training. To give readers a better overall grasp of VLP, we first review its recent advances from five aspects: feature extraction, model architecture, pre-training objectives, pre-training datasets, and downstream tasks. Then, we summarize the specific VLP models in detail. Finally, we discuss the new frontiers in VLP. To the best of our knowledge, this is the first survey on VLP. We hope that this survey can shed light on future research in the VLP field.
We study few-shot acoustic event detection (AED) in this paper. Few-shot learning enables detection of new events with very limited labeled data. Compared to other research areas like computer vision, few-shot learning for audio recognition has been under-studied. We formulate few-shot AED problem and explore different ways of utilizing traditional supervised methods for this setting as well as a variety of meta-learning approaches, which are conventionally used to solve few-shot classification problem. Compared to supervised baselines, meta-learning models achieve superior performance, thus showing its effectiveness on generalization to new audio events. Our analysis including impact of initialization and domain discrepancy further validate the advantage of meta-learning approaches in few-shot AED.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191