We use cookies to analyze the browsing and usage of our website and to personalize your experience. You can disable these technologies at any time, but this may limit certain functionalities of the site. Read our Privacy Policy for more information.
Setting cookies
You can enable and disable the types of cookies you wish to accept. However certain choices you make could affect the services offered on our sites (e.g. suggestions, personalised ads, etc.).
Essential cookies
These cookies are necessary for the operation of the site and cannot be deactivated. (Still active)
Analytics cookies
Do you accept the use of cookies to measure the audience of our sites?
Multimedia Player
Do you accept the use of cookies to display and allow you to watch the video content hosted by our partners (YouTube, etc.)?
Publications
Efficient Planning under Partial Observability with Unnormalized Q Functions and Spectral Learning
Learning and planning in partially-observable domains is one of the most difficult problems in reinforcement learning. Traditional methods c… (see more)onsider these two problems as independent, resulting in a classical two-stage paradigm: first learn the environment dynamics and then plan accordingly. This approach, however, disconnects the two problems and can consequently lead to algorithms that are sample inefficient and time consuming. In this paper, we propose a novel algorithm that combines learning and planning together. Our algorithm is closely related to the spectral learning algorithm for predicitive state representations and offers appealing theoretical guarantees and time complexity. We empirically show on two domains that our approach is more sample and time efficient compared to classical methods.
Recent studies have significantly improved the state-of-the-art on common-sense reasoning (CSR) benchmarks like the Winograd Schema Challeng… (see more)e (WSC) and SWAG. The question we ask in this paper is whether improved performance on these benchmarks represents genuine progress towards common-sense-enabled systems. We make case studies of both benchmarks and design protocols that clarify and qualify the results of previous work by analyzing threats to the validity of previous experimental designs. Our protocols account for several properties prevalent in common-sense benchmarks including size limitations, structural regularities, and variable instance difficulty.
2019-11-01
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) (published)
Humans observe and interact with the world to acquire knowledge. However, most existing machine reading comprehension (MRC) tasks miss the i… (see more)nteractive, information-seeking component of comprehension. Such tasks present models with static documents that contain all necessary information, usually concentrated in a single short substring. Thus, models can achieve strong performance through simple word- and phrase-based pattern matching. We address this problem by formulating a novel text-based question answering task: Question Answering with Interactive Text (QAit). In QAit, an agent must interact with a partially observable text-based environment to gather information required to answer questions. QAit poses questions about the existence, location, and attributes of objects found in the environment. The data is built using a text-based game generator that defines the underlying dynamics of interaction with the environment. We propose and evaluate a set of baseline models for the QAit task that includes deep reinforcement learning agents. Experiments show that the task presents a major challenge for machine reading systems, while humans solve it with relative ease.
2019-11-01
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) (published)
We present a reduction from reinforcement learning (RL) to no-regret online learning based on the saddle-point formulation of RL, by which "… (see more)any" online algorithm with sublinear regret can generate policies with provable performance guarantees. This new perspective decouples the RL problem into two parts: regret minimization and function approximation. The first part admits a standard online-learning analysis, and the second part can be quantified independently of the learning algorithm. Therefore, the proposed reduction can be used as a tool to systematically design new RL algorithms. We demonstrate this idea by devising a simple RL algorithm based on mirror descent and the generative-model oracle. For any
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) (published)
Collegiality is frequently portrayed as an inherent characteristic of professions, associated with normative expectations autonomously deter… (see more)mined and regulated among peers. However, in advanced modernity other modes of governance responding to societal expectations and increasing state reliance on professional expertise often appear in tension with conditions of collegiality. This article argues that collegiality is not an immutable and inherent characteristic of the governance of professional work and organizations; rather, it is the result of the ability of a profession to operationalize the normative, relational, and structural requirements of collegiality at work. This article builds on different streams of scholarship to present a dynamic approach to collegiality based on political work by professionals to protect, maintain, and reformulate collegiality as a core set of principles governing work. Productive resistance and co-production are explored for their contribution to collegiality in this context, enabling accommodation between professions and organizations to achieve collective objectives and serving as a vector of change and adaptation of professional work in contemporary organizations. Engagement in co-production influences the ability to materialize collegiality at work, just as the maintenance and transformation of collegiality will operate in a context where professions participate and negotiate compromises with others legitimate modes of governance. Our arguments build on recent studies and hypotheses concerning the interface of professions and organizations to reveal the political work that underlies the affirmation and re-affirmation of collegiality as a mode of governance of work based on resistance and co-production.
2019-10-24
Journal of Professions and Organization (published)
We release the largest public ECG dataset of continuous raw signals for representation learning containing 11 thousand patients and 2 billio… (see more)n labelled beats. Our goal is to enable semi-supervised ECG models to be made as well as to discover unknown subtypes of arrhythmia and anomalous ECG signal events. To this end, we propose an unsupervised representation learning task, evaluated in a semi-supervised fashion. We provide a set of baselines for different feature extractors that can be built upon. Additionally, we perform qualitative evaluations on results from PCA embeddings, where we identify some clustering of known subtypes indicating the potential for representation learning in arrhythmia sub-type discovery.
Continual learning consists in incrementally training a model on a sequence of datasets and testing on the union of all datasets. In this pa… (see more)per, we examine continual learning for the problem of sound classification, in which we wish to refine already trained models to learn new sound classes. In practice one does not want to maintain all past training data and retrain from scratch, but naively updating a model with new data(sets) results in a degradation of already learned tasks, which is referred to as "catastrophic forgetting." We develop a generative replay procedure for generating training audio spectrogram data, in place of keeping older training datasets. We show that by incrementally refining a classifier with generative replay a generator that is 4% of the size of all previous training data matches the performance of refining the classifier keeping 20% of all previous training data. We thus conclude that we can extend a trained sound classifier to learn new classes without having to keep previously used datasets.
2019-10-20
2019 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA) (published)
