Search Results for author: Daan Wierstra

Found 29 papers, 20 papers with code

Towards Interpretable Reinforcement Learning Using Attention Augmented Agents

1 code implementation NeurIPS 2019 Alex Mott, Daniel Zoran, Mike Chrzanowski, Daan Wierstra, Danilo J. Rezende

Inspired by recent work in attention models for image captioning and question answering, we present a soft attention model for the reinforcement learning domain.

Image Captioning Question Answering +1

Learning to Search with MCTSnets

2 code implementations ICML 2018 Arthur Guez, Théophane Weber, Ioannis Antonoglou, Karen Simonyan, Oriol Vinyals, Daan Wierstra, Rémi Munos, David Silver

They are most typically solved by tree search algorithms that simulate ahead into the future, evaluate future states, and back-up those evaluations to the root of a search tree.

Learning model-based planning from scratch

1 code implementation19 Jul 2017 Razvan Pascanu, Yujia Li, Oriol Vinyals, Nicolas Heess, Lars Buesing, Sebastien Racanière, David Reichert, Théophane Weber, Daan Wierstra, Peter Battaglia

Here we introduce the "Imagination-based Planner", the first model-based, sequential decision-making agent that can learn to construct, evaluate, and execute plans.

Continuous Control Decision Making

Comparison of Maximum Likelihood and GAN-based training of Real NVPs

no code implementations15 May 2017 Ivo Danihelka, Balaji Lakshminarayanan, Benigno Uria, Daan Wierstra, Peter Dayan

We train a generator by maximum likelihood and we also train the same generator architecture by Wasserstein GAN.

One-Shot Learning

Recurrent Environment Simulators

no code implementations7 Apr 2017 Silvia Chiappa, Sébastien Racaniere, Daan Wierstra, Shakir Mohamed

Models that can simulate how environments change in response to actions can be used by agents to plan and act efficiently.

Atari Games Car Racing

PathNet: Evolution Channels Gradient Descent in Super Neural Networks

1 code implementation30 Jan 2017 Chrisantha Fernando, Dylan Banarse, Charles Blundell, Yori Zwols, David Ha, Andrei A. Rusu, Alexander Pritzel, Daan Wierstra

It is a neural network algorithm that uses agents embedded in the neural network whose task is to discover which parts of the network to re-use for new tasks.

Continual Learning reinforcement-learning +1

Variational Intrinsic Control

1 code implementation22 Nov 2016 Karol Gregor, Danilo Jimenez Rezende, Daan Wierstra

In this paper we introduce a new unsupervised reinforcement learning method for discovering the set of intrinsic options available to an agent.

reinforcement-learning Unsupervised Reinforcement Learning

Model-Free Episodic Control

3 code implementations14 Jun 2016 Charles Blundell, Benigno Uria, Alexander Pritzel, Yazhe Li, Avraham Ruderman, Joel Z. Leibo, Jack Rae, Daan Wierstra, Demis Hassabis

State of the art deep reinforcement learning algorithms take many millions of interactions to attain human-level performance.

Decision Making Hippocampus +1

One-shot Learning with Memory-Augmented Neural Networks

11 code implementations19 May 2016 Adam Santoro, Sergey Bartunov, Matthew Botvinick, Daan Wierstra, Timothy Lillicrap

Despite recent breakthroughs in the applications of deep neural networks, one setting that presents a persistent challenge is that of "one-shot learning."

One-Shot Learning

Towards Conceptual Compression

1 code implementation NeurIPS 2016 Karol Gregor, Frederic Besse, Danilo Jimenez Rezende, Ivo Danihelka, Daan Wierstra

We introduce a simple recurrent variational auto-encoder architecture that significantly improves image modeling.

Ranked #55 on Image Generation on CIFAR-10 (bits/dimension metric)

Image Generation

One-Shot Generalization in Deep Generative Models

no code implementations16 Mar 2016 Danilo Jimenez Rezende, Shakir Mohamed, Ivo Danihelka, Karol Gregor, Daan Wierstra

In particular, humans have an ability for one-shot generalization: an ability to encounter a new concept, understand its structure, and then be able to generate compelling alternative variations of the concept.

Density Estimation Image Generation

Weight Uncertainty in Neural Networks

33 code implementations20 May 2015 Charles Blundell, Julien Cornebise, Koray Kavukcuoglu, Daan Wierstra

We introduce a new, efficient, principled and backpropagation-compatible algorithm for learning a probability distribution on the weights of a neural network, called Bayes by Backprop.

Bayesian Inference General Classification +1

Human level control through deep reinforcement learning

2 code implementations25 Feb 2015 Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Andrei A. Rusu, Joel Veness, Marc G. Bellemare, Alex Graves, Martin Riedmiller, Andreas K. Fidjeland, Georg Ostrovski, Stig Petersen, Charles Beattie, Amir Sadik, Ioannis Antonoglou, Helen King, Dharshan Kumaran, Daan Wierstra, Shane Legg1 & Demis Hassabis

We demonstrate that the deep Q-network agent, receiving only the pixels and the game score as inputs, was able to surpass the performance of all previous algorithms and achieve a level comparable to that of a professional human games tester across a set of 49 games, using the same algorithm, network architecture and hyperparameters.

Atari Games reinforcement-learning

DRAW: A Recurrent Neural Network For Image Generation

20 code implementations16 Feb 2015 Karol Gregor, Ivo Danihelka, Alex Graves, Danilo Jimenez Rezende, Daan Wierstra

This paper introduces the Deep Recurrent Attentive Writer (DRAW) neural network architecture for image generation.

Ranked #61 on Image Generation on CIFAR-10 (bits/dimension metric)

Foveation Image Generation

Stochastic Backpropagation and Approximate Inference in Deep Generative Models

5 code implementations16 Jan 2014 Danilo Jimenez Rezende, Shakir Mohamed, Daan Wierstra

We marry ideas from deep neural networks and approximate Bayesian inference to derive a generalised class of deep, directed generative models, endowed with a new algorithm for scalable inference and learning.

Bayesian Inference

Playing Atari with Deep Reinforcement Learning

96 code implementations19 Dec 2013 Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Alex Graves, Ioannis Antonoglou, Daan Wierstra, Martin Riedmiller

We present the first deep learning model to successfully learn control policies directly from high-dimensional sensory input using reinforcement learning.

Atari Games Q-Learning +1

Deep AutoRegressive Networks

no code implementations31 Oct 2013 Karol Gregor, Ivo Danihelka, andriy mnih, Charles Blundell, Daan Wierstra

We introduce a deep, generative autoencoder capable of learning hierarchies of distributed representations from data.

Atari Games

Variational Learning for Recurrent Spiking Networks

no code implementations NeurIPS 2011 Danilo J. Rezende, Daan Wierstra, Wulfram Gerstner

We derive a plausible learning rule updating the synaptic efficacies for feedforward, feedback and lateral connections between observed and latent neurons.

Variational Inference

Natural Evolution Strategies

1 code implementation22 Jun 2011 Daan Wierstra, Tom Schaul, Tobias Glasmachers, Yi Sun, Jürgen Schmidhuber

This paper presents Natural Evolution Strategies (NES), a recent family of algorithms that constitute a more principled approach to black-box optimization than established evolutionary algorithms.

Cannot find the paper you are looking for? You can Submit a new open access paper.