
Recurrent Independent Mechanisms
Learning modular structures which reflect the dynamics of the environmen...
read it

Learning Neural Causal Models from Unknown Interventions
Metalearning over a set of distributions can be interpreted as learning...
read it

SmallGAN: Speeding Up GAN Training Using Coresets
Recent work by Brock et al. (2018) suggests that Generative Adversarial ...
read it

InfoBot: Transfer and Exploration via the Information Bottleneck
A central challenge in reinforcement learning is discovering effective p...
read it

Communication Topologies Between Learning Agents in Deep Reinforcement Learning
A common technique to improve speed and robustness of learning in deep r...
read it

Learning Dynamics Model in Reinforcement Learning by Incorporating the Long Term Future
In modelbased reinforcement learning, the agent interleaves between mod...
read it

Learning Powerful Policies by Using Consistent Dynamics Model
Modelbased Reinforcement Learning approaches have the promise of being ...
read it

Learning the Arrow of Time
We humans seem to have an innate understanding of the asymmetric progres...
read it

Reinforcement Learning with Competitive Ensembles of InformationConstrained Primitives
Reinforcement learning agents that operate in diverse and complex enviro...
read it

Maximum Entropy Generators for EnergyBased Models
Unsupervised learning is about capturing dependencies between variables ...
read it

ZForcing: Training Stochastic Recurrent Networks
Many efforts have been devoted to training generative latent variable mo...
read it

ACtuAL: ActorCritic Under Adversarial Learning
Generative Adversarial Networks (GANs) are a powerful framework for deep...
read it

Professor Forcing: A New Algorithm for Training Recurrent Networks
The Teacher Forcing algorithm trains recurrent networks by supplying obs...
read it

Zoneout: Regularizing RNNs by Randomly Preserving Hidden Activations
We propose zoneout, a novel method for regularizing RNNs. At each timest...
read it

Stories in the Eye: Contextual Visual Interactions for Efficient Video to Language Translation
Integrating higher level visual and linguistic interpretations is at the...
read it

Sparse Attentive Backtracking: LongRange Credit Assignment in Recurrent Networks
A major drawback of backpropagation through time (BPTT) is the difficult...
read it

Variational Walkback: Learning a Transition Operator as a Stochastic Recurrent Net
We propose a novel method to directly learn a stochastic transition oper...
read it

Recall Traces: Backtracking Models for Efficient Reinforcement Learning
In many environments only a tiny subset of all states yield high reward....
read it

Fortified Networks: Improving the Robustness of Deep Networks by Modeling the Manifold of Hidden Representations
Deep networks have achieved impressive results across a variety of impor...
read it

Generalization of Equilibrium Propagation to Vector Field Dynamics
The biological plausibility of the backpropagation algorithm has long be...
read it

Sparse Attentive Backtracking: Temporal CreditAssignment Through Reminding
Learning longterm dependencies in extended temporal sequences requires ...
read it

A MetaTransfer Objective for Learning to Disentangle Causal Mechanisms
We propose to metalearn causal structures based on how fast a learner a...
read it

StateReification Networks: Improving Generalization by Modeling the Distribution of Hidden Representations
Machine learning promises methods that generalize well from finite label...
read it
Anirudh Goyal
is this you? claim profile