Publications

Recurrent Value Functions

Pierre Thodoroff

Nishanth Anand

Lucas Caccia

Joelle Pineau

Despite recent successes in Reinforcement Learning, value-based methods often suffer from high variance hindering performance. In this paper… (voir plus), we illustrate this in a continuous control setting where state of the art methods perform poorly whenever sensor noise is introduced. To overcome this issue, we introduce Recurrent Value Functions (RVFs) as an alternative to estimate the value function of a state. We propose to estimate the value function of the current state using the value function of past states visited along the trajectory. Due to the nature of their formulation, RVFs have a natural way of learning an emphasis function that selectively emphasizes important states. First, we establish RVF's asymptotic convergence properties in tabular settings. We then demonstrate their robustness on a partially observable domain and continuous control tasks. Finally, we provide a qualitative interpretation of the learned emphasis function.

2018-12-31

arXiv (prépublication)

doi.org

Reza Babanezhad Harikandeh

Reducing the variance in online optimization by transporting past gradients

Sébastien M. R. Arnold

Pierre-Antoine Manzagol

Ioannis Mitliagkas

Nicolas Roux

Most stochastic optimization methods use gradients once before discarding them. While variance reduction methods have shown that reusing pas… (voir plus)t gradients can be beneficial when there is a finite number of datapoints, they do not easily extend to the online setting. One issue is the staleness due to using past gradients. We propose to correct this staleness using the idea of implicit gradient transport (IGT) which transforms gradients computed at previous iterates into gradients evaluated at the current iterate without using the Hessian explicitly. In addition to reducing the variance and bias of our updates over time, IGT can be used as a drop-in replacement for the gradient estimate in a number of well-understood methods such as heavy ball or Adam. We show experimentally that it achieves state-of-the-art results on a wide range of architectures and benchmarks. Additionally, the IGT gradient estimator yields the optimal asymptotic convergence rate for online stochastic optimization in the restricted setting where the Hessians of all component functions are equal.

2018-12-31

Advances in Neural Information Processing Systems 32 (NeurIPS 2019) (publié)

Reinforcement Learning for Sustainable Agriculture

Jonathan Binas

Leonie H. Luginbuehl

Yoshua Bengio

Modern machine learning methods have achieved superhuman performance on a variety of tasks, simply learning from the outcomes of their actio… (voir plus)ns. We propose a path towards more sustainable agriculture, considering plant development an optimization problem with respect to certain parameters, such as yield and environmental impact, which can be optimized in an automated way. Specifically, we propose to use reinforcement learning to autonomously explore and learn ways of influencing the development of certain types of plants, controlling environmental parameters, such as irrigation or nutrient supply, and receiving sensory feedback, such as camera images, humidity, and moisture measurements. The trained system will thus be able to provide instructions for optimal treatment of a local population of plants, based on non-invasive measurements, such as imaging.

2018-12-31

(publié)

www.semanticscholar.org

Saliency Is a Possible Red Herring When Diagnosing Poor Generalization

Joseph D. Viviano

Becks Simpson

Francis Dutil

Yoshua Bengio

Joseph Paul Cohen

Poor generalization is one symptom of models that learn to predict target variables using spuriously-correlated image features present only … (voir plus)in the training distribution instead of the true image features that denote a class. It is often thought that this can be diagnosed visually using attribution (aka saliency) maps. We study if this assumption is correct. In some prediction tasks, such as for medical images, one may have some images with masks drawn by a human expert, indicating a region of the image containing relevant information to make the prediction. We study multiple methods that take advantage of such auxiliary labels, by training networks to ignore distracting features which may be found outside of the region of interest. This mask information is only used during training and has an impact on generalization accuracy depending on the severity of the shift between the training and test distributions. Surprisingly, while these methods improve generalization performance in the presence of a covariate shift, there is no strong correspondence between the correction of attribution towards the features a human expert has labelled as important and generalization performance. These results suggest that the root cause of poor generalization may not always be spatially defined, and raise questions about the utility of masks as "attribution priors" as well as saliency maps for explainable predictions.

2018-12-31

arXiv (prépublication)

doi.org

La science, un droit humain. Mettre en œuvre le principe d’une science participative, équitable et accessible à tous

Catherine Régis

2018-12-31

(publié)

www.semanticscholar.org

Systematic Generalization: What Is Required and Can It Be Learned?

Dzmitry Bahdanau*

Shikhar Murty*

2018-12-31

ICLR.cc/2019/Conference (poster)

Temporally Extended Metrics for Markov Decision Processes.

Philip Amortila

Bellemare Marc-Emmanuel

Prakash Panangaden

2018-12-31

SafeAI@AAAI (publié)

dblp.uni-trier.de

The Option Keyboard: Combining Skills in Reinforcement Learning

Andre Barreto

Diana Borsa

Shaobo Hou

Gheorghe Comanici

Eser Aygün

Philippe Hamel

Daniel Toyama

Jonathan J. Hunt

Shibl Mourad

David Silver

The ability to combine known skills to create new ones may be crucial in the solution of complex reinforcement learning problems that unfold… (voir plus) over extended periods. We argue that a robust way of combining skills is to define and manipulate them in the space of pseudo-rewards (or "cumulants"). Based on this premise, we propose a framework for combining skills using the formalism of options. We show that every deterministic option can be unambiguously represented as a cumulant defined in an extended domain. Building on this insight and on previous results on transfer learning, we show how to approximate options whose cumulants are linear combinations of the cumulants of known options. This means that, once we have learned options associated with a set of cumulants, we can instantaneously synthesise options induced by any linear combination of them, without any learning involved. We describe how this framework provides a hierarchical interface to the environment whose abstract actions correspond to combinations of basic skills. We demonstrate the practical benefits of our approach in a resource management problem and a navigation task involving a quadrupedal simulated robot.

2018-12-31

NeurIPS (publié)

On the Relation Between the Sharpest Directions of DNN Loss and the SGD Step Length

Stanisław Jastrzębski

Amos Storkey

Stochastic Gradient Descent (SGD) based training of neural networks with a large learning rate or a small batch-size typically ends in well-… (voir plus)generalizing, flat regions of the weight space, as indicated by small eigenvalues of the Hessian of the training loss. However, the curvature along the SGD trajectory is poorly understood. An empirical investigation shows that initially SGD visits increasingly sharp regions, reaching a maximum sharpness determined by both the learning rate and the batch-size of SGD. When studying the SGD dynamics in relation to the sharpest directions in this initial phase, we find that the SGD step is large compared to the curvature and commonly fails to minimize the loss along the sharpest directions. Furthermore, using a reduced learning rate along these directions can improve training speed while leading to both sharper and better generalizing solutions compared to vanilla SGD. In summary, our analysis of the dynamics of SGD in the subspace of the sharpest directions shows that they influence the regions that SGD steers to (where larger learning rate or smaller batch size result in wider regions visited), the overall training speed, and the generalization ability of the final model.

2018-12-31

ICLR.cc/2019/Conference (poster)

On the Spectral Bias of Neural Networks

Nasim Rahaman

Felix Draxler

Fred A. Hamprecht

Neural networks are known to be a class of highly expressive functions able to fit even random input-output mappings with …

2018-12-31

ICML (publié)

doi.org

proceedings.mlr.press

The Termination Critic

Anna Harutyunyan

Will Dabney

Diana Borsa

Nicolas Heess

Remi Munos

In this work, we consider the problem of autonomously discovering behavioral abstractions, or options, for reinforcement learning agents. We… (voir plus) propose an algorithm that focuses on the termination function, as opposed to - as is common - the policy. The termination function is usually trained to optimize a control objective: an option ought to terminate if another has better value. We offer a different, information-theoretic perspective, and propose that terminations should focus instead on the compressibility of the option’s encoding - arguably a key reason for using abstractions.To achieve this algorithmically, we leverage the classical options framework, and learn the option transition model as a “critic” for the termination function. Using this model, we derive gradients that optimize the desired criteria. We show that the resulting options are non-trivial, intuitively meaningful, and useful for learning.

2018-12-31

AISTATS (publié)