(Rex) Devon Hjelm

Data-Efficient Reinforcement Learning with Momentum Predictive Representations

Max Schwarzer

Ankesh Anand

Rishab Goel

Aaron Courville

Philip Bachman

While deep reinforcement learning excels at solving tasks where large amounts of data can be collected through virtually unlimited interacti… (see more)on with the environment, learning from limited interaction remains a key challenge. We posit that an agent can learn more efficiently if we augment reward maximization with self-supervised objectives based on structure in its visual input and sequential interaction with the environment. Our method, Momentum Predictive Representations (MPR), trains an agent to predict its own latent state representations multiple steps into the future. We compute target representations for future states using an encoder which is an exponential moving average of the agent's parameters, and we make predictions using a learned transition model. On its own, this future prediction objective outperforms prior methods for sample-efficient deep RL from pixels. We further improve performance by adding data augmentation to the future prediction loss, which forces the agent's representations to be consistent across multiple views of an observation. Our full self-supervised objective, which combines future prediction and data augmentation, achieves a median human-normalized score of 0.444 on Atari in a setting limited to 100K steps of environment interaction, which is a 66% relative improvement over the previous state-of-the-art. Moreover, even in this limited data regime, MPR exceeds expert human scores on 6 out of 26 games.

2020-07-12

arXiv.org (preprint)

dblp.uni-trier.de

Leveraging exploration in off-policy algorithms via normalizing flows

Thang Doan

Exploration is a crucial component for discovering approximately optimal policies in most high-dimensional reinforcement learning (RL) setti… (see more)ngs with sparse rewards. Approaches such as neural density models and continuous exploration (e.g., Go-Explore) have been instrumental in recent advances. Soft actor-critic (SAC) is a method for improving exploration that aims to combine off-policy updates while maximizing the policy entropy. We extend SAC to a richer class of probability distributions through normalizing flows, which we show improves performance in exploration, sample complexity, and convergence. Finally, we show that not only the normalizing flow policy outperforms SAC on MuJoCo domains, it is also significantly lighter, using as low as 5.6% of the original network's parameters for similar performance.

2020-05-12

Proceedings of the Conference on Robot Learning (published)

proceedings.mlr.press

Batch Weight for Domain Adaptation With Mass Shift

Mikolaj Binkowski

Aaron Courville

Unsupervised domain transfer is the task of transferring or translating samples from a source distribution to a different target distributio… (see more)n. Current solutions unsupervised domain transfer often operate on data on which the modes of the distribution are well-matched, for instance have the same frequencies of classes between source and target distributions. However, these models do not perform well when the modes are not well-matched, as would be the case when samples are drawn independently from two different, but related, domains. This mode imbalance is problematic as generative adversarial networks (GANs), a successful approach in this setting, are sensitive to mode frequency, which results in a mismatch of semantics between source samples and generated samples of the target distribution. We propose a principled method of re-weighting training samples to correct for such mass shift between the transferred distributions, which we call batch weight. We also provide rigorous probabilistic setting for domain transfer and new simplified objective for training transfer networks, an alternative to complex, multi-component loss functions used in the current state-of-the art image-to-image translation models. The new objective stems from the discrimination of joint distributions and enforces cycle-consistency in an abstract, high-level, rather than pixel-wise, sense. Lastly, we experimentally show the effectiveness of the proposed methods in several image-to-image translation tasks.

2019-11-02

2019 IEEE/CVF International Conference on Computer Vision (ICCV) (published)

doi.org

Tell, Draw, and Repeat: Generating and Modifying Images Based on Continual Linguistic Instruction

Alaaeldin El-Nouby

Shikhar Sharma

Hannes Schulz

Layla El Asri

Samira Ebrahimi Kahou

Graham W. Taylor

Conditional text-to-image generation is an active area of research, with many possible applications. Existing research has primarily focused… (see more) on generating a single image from available conditioning information in one step. One practical extension beyond one-step generation is a system that generates an image iteratively, conditioned on ongoing linguistic input or feedback. This is significantly more challenging than one-step generation tasks, as such a system must understand the contents of its generated images with respect to the feedback history, the current feedback, as well as the interactions among concepts present in the feedback history. In this work, we present a recurrent image generation model which takes into account both the generated output up to the current step as well as all past instructions for generation. We show that our model is able to generate the background, add new objects, and apply simple transformations to existing objects. We believe our approach is an important step toward interactive generation. Code and data is available at: https://www.microsoft.com/en-us/research/project/generative-neural-visual-artist-geneva/.

2019-11-02

2019 IEEE/CVF International Conference on Computer Vision (ICCV) (published)

doi.org

Attraction-Repulsion Actor-Critic for Continuous Control Reinforcement Learning

Thang Doan

Continuous control tasks in reinforcement learning are important because they provide an important framework for learning in high-dimensiona… (see more)l state spaces with deceptive rewards, where the agent can easily become trapped into suboptimal solutions. One way to avoid local optima is to use a population of agents to ensure coverage of the policy space, yet learning a population with the "best" coverage is still an open problem. In this work, we present a novel approach to population-based RL in continuous control that leverages properties of normalizing flows to perform attractive and repulsive operations between current members of the population and previously observed policies. Empirical results on the MuJoCo suite demonstrate a high performance gain for our algorithm compared to prior work, including Soft-Actor Critic (SAC).

2019-09-17

ArXiv (preprint)

Online Adaptative Curriculum Learning for GANs

Thang Doan

Joao Monteiro

Isabela Albuquerque

Generative Adversarial Networks (GANs) can successfully approximate a probability distribution and produce realistic samples. However, open … (see more)questions such as sufficient convergence conditions and mode collapse still persist. In this paper, we build on existing work in the area by proposing a novel framework for training the generator against an ensemble of discriminator networks, which can be seen as a one-student/multiple-teachers setting. We formalize this problem within the full-information adversarial bandit framework, where we evaluate the capability of an algorithm to select mixtures of discriminators for providing the generator with feedback during learning. To this end, we propose a reward function which reflects the progress made by the generator and dynamically update the mixture weights allocated to each discriminator. We also draw connections between our algorithm and stochastic optimization methods and then show that existing approaches using multiple discriminators in literature can be recovered from our framework. We argue that less expressive discriminators are smoother and have a general coarse grained view of the modes map, which enforces the generator to cover a wide portion of the data distribution support. On the other hand, highly expressive discriminators ensure samples quality. Finally, experimental results show that our approach improves samples quality and diversity over existing baselines by effectively learning a curriculum. These results also support the claim that weaker discriminators have higher entropy improving modes coverage.

2019-07-17

Proceedings of the AAAI Conference on Artificial Intelligence (published)

doi.org

On Adversarial Mixup Resynthesis

Christopher Beckham

Sina Honari

Alex Lamb

Vikas Verma

Farnoosh Ghadiri

Chris Pal

In this paper, we explore new approaches to combining information encoded within the learned representations of auto-encoders. We explore mo… (see more)dels that are capable of combining the attributes of multiple inputs such that a resynthesised output is trained to fool an adversarial discriminator for real versus synthesised data. Furthermore, we explore the use of such an architecture in the context of semi-supervised learning, where we learn a mixing function whose objective is to produce interpolations of hidden states, or masked combinations of latent representations that are consistent with a conditioned class label. We show quantitative and qualitative evidence that such a formulation is an interesting avenue of research.

Adversarial Mixup Resynthesizers

Christopher Beckham

Sina Honari

Alex Lamb

Vikas Verma

Farnoosh Ghadiri

Chris Pal

In this paper, we explore new approaches to combining information encoded within the learned representations of autoencoders. We explore mod… (see more)els that are capable of combining the attributes of multiple inputs such that a resynthesised output is trained to fool an adversarial discriminator for real versus synthesised data. Furthermore, we explore the use of such an architecture in the context of semi-supervised learning, where we learn a mixing function whose objective is to produce interpolations of hidden states, or masked combinations of latent representations that are consistent with a conditioned class label. We show quantitative and qualitative evidence that such a formulation is an interesting avenue of research.

2019-01-01

DGS@ICLR (published)

Deep Graph Infomax

Petar Veličković

William Fedus

William L. Hamilton

Pietro Lio

We present Deep Graph Infomax (DGI), a general approach for learning node representations within graph-structured data in an unsupervised ma… (see more)nner. DGI relies on maximizing mutual information between patch representations and corresponding high-level summaries of graphs---both derived using established graph convolutional network architectures. The learnt patch representations summarize subgraphs centered around nodes of interest, and can thus be reused for downstream node-wise learning tasks. In contrast to most prior approaches to unsupervised learning with GCNs, DGI does not rely on random walk objectives, and is readily applicable to both transductive and inductive learning setups. We demonstrate competitive performance on a variety of node classification benchmarks, which at times even exceeds the performance of supervised learning.

2019-01-01

ICLR (Poster) (published)

Deep Graph Infomax

Petar Veličković

William Fedus

William L. Hamilton

Pietro Lio

We present Deep Graph Infomax (DGI), a general approach for learning node representations within graph-structured data in an unsupervised ma… (see more)nner. DGI relies on maximizing mutual information between patch representations and corresponding high-level summaries of graphs---both derived using established graph convolutional network architectures. The learnt patch representations summarize subgraphs centered around nodes of interest, and can thus be reused for downstream node-wise learning tasks. In contrast to most prior approaches to unsupervised learning with GCNs, DGI does not rely on random walk objectives, and is readily applicable to both transductive and inductive learning setups. We demonstrate competitive performance on a variety of node classification benchmarks, which at times even exceeds the performance of supervised learning.

2019-01-01

ICLR.cc/2019/Conference (poster)

Learning deep representations by mutual information estimation and maximization

Alex Fedorov

Samuel Lavoie-Marchildon

Karan Grewal

Adam Trischler

Phil Bachman

This work investigates unsupervised learning of representations by maximizing mutual information between an input and the output of a deep n… (see more)eural network encoder. Importantly, we show that structure matters: incorporating knowledge about locality in the input into the objective can significantly improve a representation’s suitability for downstream tasks. We further control characteristics of the representation by matching to a prior distribution adversarially. Our method, which we call Deep InfoMax (DIM), outperforms a number of popular unsupervised learning methods and compares favorably with fully-supervised learning on several classification tasks in with some standard architectures. DIM opens new avenues for unsupervised learning of representations and is an important step towards flexible formulations of representation learning objectives for specific end-goals.

2019-01-01

ICLR (published)