Search Results for author:
Found 19 papers, 9 papers with code
Procedural Generalization by Planning with Self-Supervised World Models
One of the key promises of model-based reinforcement learning is the ability to generalize using an internal model of the world to make predictions in novel environments and tasks.
Ranked #1 on
Meta-Learning
on ML10
(Meta-test success rate (zero-shot) metric)
Planning in Stochastic Environments with a Learned Model
However, previous instantiations of this approach were limited to the use of deterministic models.
Pretrained Encoders are All You Need
Data-efficiency and generalization are key challenges in deep learning and deep reinforcement learning as many models are trained on large-scale, domain-specific, and expensive-to-label datasets.
Vector Quantized Models for Planning
Our key insight is to use discrete autoencoders to capture the multiple possible effects of an action in a stochastic environment.
SketchTransfer: A Challenging New Task for Exploring Detail-Invariance and the Abstractions Learned by Deep Networks
In this work we focus on their ability to have invariance towards the presence or absence of details.
Unsupervised State Representation Learning in Atari
State representation learning, or the ability to capture latent generative factors of an environment, is crucial for building intelligent agents that can perform a wide variety of tasks.
The Journey is the Reward: Unsupervised Learning of Influential Trajectories
Unsupervised exploration and representation learning become increasingly important when learning in diverse and sparse environments.
On Variational Bounds of Mutual Information
Estimating and optimizing Mutual Information (MI) is core to many problems in machine learning; however, bounding MI in high dimensions is challenging.
Wasserstein Dependency Measure for Representation Learning
Mutual information maximization has emerged as a powerful learning objective for unsupervised representation learning obtaining state-of-the-art performance in applications such as object recognition, speech recognition, and reinforcement learning.
Maximum Entropy Generators for Energy-Based Models
Maximum likelihood estimation of energy-based models is a challenging problem due to the intractability of the log-likelihood gradient.
Mutual Information Neural Estimation
We argue that the estimation of mutual information between high dimensional continuous random variables can be achieved by gradient descent over neural networks.
MINE: Mutual Information Neural Estimation
We argue that the estimation of mutual information between high dimensional continuous random variables can be achieved by gradient descent over neural networks.
Learning Generative Models with Locally Disentangled Latent Factors
One of the most successful techniques in generative models has been decomposing a complicated generation task into a series of simpler generation tasks.
Deep Speech 2: End-to-End Speech Recognition in English and Mandarin
We show that an end-to-end deep learning approach can be used to recognize either English or Mandarin Chinese speech--two vastly different languages.
Ranked #1 on
Noisy Speech Recognition
on CHiME clean
Generative Adversarial Nets
We propose a new framework for estimating generative models via adversarial nets, in which we simultaneously train two models: a generative model G that captures the data distribution, and a discriminative model D that estimates the probability that a sample came from the training data rather than G. The training procedure for G is to maximize the probability of D making a mistake.
Deep Directed Generative Autoencoders
The objective is to learn an encoder $f(\cdot)$ that maps $X$ to $f(X)$ that has a much simpler distribution than $X$ itself, estimated by $P(H)$.
On the Equivalence Between Deep NADE and Generative Stochastic Networks
Orderless NADEs are trained based on a criterion that stochastically maximizes $P(\mathbf{x})$ with all possible orders of factorizations.
Generative Adversarial Networks
We propose a new framework for estimating generative models via an adversarial process, in which we simultaneously train two models: a generative model G that captures the data distribution, and a discriminative model D that estimates the probability that a sample came from the training data rather than G. The training procedure for G is to maximize the probability of D making a mistake.
Super-Resolution
Time-Series Few-Shot Learning with Heterogeneous Channels
Multimodal Transitions for Generative Stochastic Networks
Generative Stochastic Networks (GSNs) have been recently introduced as an alternative to traditional probabilistic modeling: instead of parametrizing the data distribution directly, one parametrizes a transition operator for a Markov chain whose stationary distribution is an estimator of the data generating distribution.
