Joelle Pineau

Doina Precup

Several applications of Reinforcement Learning suffer from instability due to high variance. This is especially prevalent in high dimensiona… (voir plus)l domains. Regularization is a commonly used technique in machine learning to reduce variance, at the cost of introducing some bias. Most existing regularization techniques focus on spatial (perceptual) regularization. Yet in reinforcement learning, due to the nature of the Bellman equation, there is an opportunity to also exploit temporal regularization based on smoothness in value estimates over trajectories. This paper explores a class of methods for temporal regularization. We formally characterize the bias induced by this technique using Markov chain concepts. We illustrate the various characteristics of temporal regularization via a sequence of simple discrete and continuous MDPs, and show that the technique provides improvement even in high-dimensional Atari games.

Tensor Regression Networks with various Low-Rank Tensor Approximations

Xingwei Cao

Guillaume Rabusseau

Tensor regression networks achieve high compression rate of neural networks while having slight impact on performances. They do so by imposi… (voir plus)ng low tensor rank structure on the weight matrices of fully connected layers. In recent years, tensor regression networks have been investigated from the perspective of their compressive power, however, the regularization effect of enforcing low-rank tensor structure has not been investigated enough. We study tensor regression networks using various low-rank tensor approximations, aiming to compare the compressive and regularization power of different low-rank constraints. We evaluate the compressive and regularization performances of the proposed model with both deep and shallow convolutional neural networks. The outcome of our experiment suggests the superiority of Global Average Pooling Layer over Tensor Regression Layer when applied to deep convolutional neural network with CIFAR-10 dataset. On the contrary, shallow convolutional neural networks with tensor regression layer and dropout achieved lower test error than both Global Average Pooling and fully-connected layer with dropout function when trained with a small number of samples.

2017-12-27

ArXiv (prépublication)

ACtuAL: Actor-Critic Under Adversarial Learning

Anirudh Goyal

Nan Rosemary Ke

Alex Lamb

Generative Adversarial Networks (GANs) are a powerful framework for deep generative modeling. Posed as a two-player minimax problem, GANs ar… (voir plus)e typically trained end-to-end on real-valued data and can be used to train a generator of high-dimensional and realistic images. However, a major limitation of GANs is that training relies on passing gradients from the discriminator through the generator via back-propagation. This makes it fundamentally difficult to train GANs with discrete data, as generation in this case typically involves a non-differentiable function. These difficulties extend to the reinforcement learning setting when the action space is composed of discrete decisions. We address these issues by reframing the GAN framework so that the generator is no longer trained using gradients through the discriminator, but is instead trained using a learned critic in the actor-critic framework with a Temporal Difference (TD) objective. This is a natural fit for sequence modeling and we use it to achieve improvements on language modeling tasks over the standard Teacher-Forcing methods.

2017-11-13

ArXiv (prépublication)

Predicting Success in Goal-Driven Human-Human Dialogues

Michael Noseworthy

Jackie Cheung

In goal-driven dialogue systems, success is often defined based on a structured definition of the goal. This requires that the dialogue syst… (voir plus)em be constrained to handle a specific class of goals and that there be a mechanism to measure success with respect to that goal. However, in many human-human dialogues the diversity of goals makes it infeasible to define success in such a way. To address this scenario, we consider the task of automatically predicting success in goal-driven human-human dialogues using only the information communicated between participants in the form of text. We build a dataset from stackoverflow.com which consists of exchanges between two users in the technical domain where ground-truth success labels are available. We then propose a turn-based hierarchical neural network model that can be used to predict success without requiring a structured goal definition. We show this model outperforms rule-based heuristics and other baselines as it is able to detect patterns over the course of a dialogue and capture notions such as gratitude.

2017-08-01

SIGDIAL Conference (publié)

Multi-modal Variational Encoder-Decoders

Iulian V. Serban

Alexander G. Ororbia II

Aaron Courville

Recent advances in neural variational inference have facilitated efficient training of powerful directed graphical models with continuous la… (voir plus)tent variables, such as variational autoencoders. However, these models usually assume simple, uni-modal priors — such as the multivariate Gaussian distribution — yet many real-world data distributions are highly complex and multi-modal. Examples of complex and multi-modal distributions range from topics in newswire text to conversational dialogue responses. When such latent variable models are applied to these domains, the restriction of the simple, uni-modal prior hinders the overall expressivity of the learned model as it cannot possibly capture more complex aspects of the data distribution. To overcome this critical restriction, we propose a flexible, simple prior distribution which can be learned efficiently and potentially capture an exponential number of modes of a target distribution. We develop the multi-modal variational encoder-decoder framework and investigate the effectiveness of the proposed prior in several natural language processing modeling tasks, including document modeling and dialogue modeling.

2017-04-24

arXiv.org (prépublication)

openreview.net

A Sparse Probabilistic Model of User Preference Data

Matthew J. A. Smith

Laurent Charlin

2017-04-11

Advances in Artificial Intelligence (publié)

A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues

Iulian V. Serban

Ryan Lowe

Sequential data often possesses hierarchical structures with complex dependencies between sub-sequences, such as found between the utterance… (voir plus)s in a dialogue. To model these dependencies in a generative framework, we propose a neural network-based generative architecture, with stochastic latent variables that span a variable number of time steps. We apply the proposed model to the task of dialogue response generation and compare it with other recent neural-network architectures. We evaluate the model performance through a human evaluation study. The experiments demonstrate that our model improves upon recently proposed models and that the latent variables facilitate both the generation of meaningful, long and diverse responses and maintaining dialogue state.

2017-02-12

Proceedings of the AAAI Conference on Artificial Intelligence (publié)

Training End-to-End Dialogue Systems with the Ubuntu Dialogue Corpus

Ryan Thomas Lowe

Nissan Pow

Iulian V. Serban

Laurent Charlin

Chia-Wei Liu

In this paper, we construct and train end-to-end neural network-based dialogue systems using an updated version of the recent Ubuntu Dialogu… (voir plus)e Corpus, a dataset containing almost 1 million multi-turn dialogues, with a total of over 7 million utterances and 100 million words. This dataset is interesting because of its size, long context lengths, and technical nature; thus, it can be used to train large models directly from data with minimal feature engineering, which can be both time consuming and expensive. We provide baselines in two different environments: one where models are trained to maximize the log-likelihood of a generated utterance conditioned on the context of the conversation, and one where models are trained to select the correct next response from a list of candidate responses. These are both evaluated on a recall task that we call Next Utterance Classification (NUC), as well as other generation-specific metrics. Finally, we provide a qualitative error analysis to help determine the most promising directions for future research on the Ubuntu Dialogue Corpus, and for end-to-end dialogue systems in general.

2017-01-20

Dialogue & Discourse (publié)

Multitask Spectral Learning of Weighted Automata

Guillaume Rabusseau

Borja Balle

We consider the problem of estimating multiple related functions computed by weighted automata~(WFA). We first present a natural notion of r… (voir plus)elatedness between WFAs by considering to which extent several WFAs can share a common underlying representation. We then introduce the model of vector-valued WFA which conveniently helps us formalize this notion of relatedness. Finally, we propose a spectral learning algorithm for vector-valued WFAs to tackle the multitask learning problem. By jointly learning multiple tasks in the form of a vector-valued WFA, our algorithm enforces the discovery of a representation space shared between tasks. The benefits of the proposed multitask approach are theoretically motivated and showcased through experiments on both synthetic and real world datasets.

Piecewise Latent Variables for Neural Variational Text Processing

Iulian V. Serban

Alexander G. Ororbia II

Aaron Courville

Advances in neural variational inference have facilitated the learning of powerful directed graphical models with continuous latent variable… (voir plus)s, such as variational autoencoders. The hope is that such models will learn to represent rich, multi-modal latent factors in real-world data, such as natural language text. However, current models often assume simplistic priors on the latent variables - such as the uni-modal Gaussian distribution - which are incapable of representing complex latent factors efficiently. To overcome this restriction, we propose the simple, but highly flexible, piecewise constant distribution. This distribution has the capacity to represent an exponential number of modes of a latent target distribution, while remaining mathematically tractable. Our results demonstrate that incorporating this new latent distribution into different models yields substantial improvements in natural language processing tasks such as document modeling and natural language generation for dialogue.

2017-01-01

Conference on Empirical Methods in Natural Language Processing (publié)

Recent Advances in Reinforcement Learning

2008-01-01

Lecture Notes in Computer Science (publié)

Recent Advances in Reinforcement Learning

2008-01-01

Lecture Notes in Computer Science (publié)