Daan Wierstra

发表

Human-level control through deep reinforcement learning

Shane Legg, Alex Graves, Marc G. Bellemare, 2015, Nature.

Relational inductive biases, deep learning, and graph networks pdf

Razvan Pascanu, H. Francis Song, Jessica B. Hamrick, 2018, ArXiv.

Continuous control with deep reinforcement learning pdf

Yuval Tassa, David Silver, Daan Wierstra, 2015, ICLR.

Deterministic Policy Gradient Algorithms

Guy Lever, Martin A. Riedmiller, David Silver, 2014, ICML.

Playing Atari with Deep Reinforcement Learning pdf

Alex Graves, Koray Kavukcuoglu, Martin A. Riedmiller, 2013, ArXiv.

Learning to Search with MCTSnets

Rémi Munos, Oriol Vinyals, Karen Simonyan, 2018, ICML.

Weight Uncertainty in Neural Networks pdf

Julien Cornebise, Koray Kavukcuoglu, Daan Wierstra, 2015, ArXiv.

Relational recurrent neural networks

Razvan Pascanu, Oriol Vinyals, Daan Wierstra, 2018, NeurIPS.

Stochastic Backpropagation and Approximate Inference in Deep Generative Models

Daan Wierstra, Shakir Mohamed, Danilo Jimenez Rezende, 2014, ICML.

Matching Networks for One Shot Learning

Oriol Vinyals, Koray Kavukcuoglu, Daan Wierstra, 2016, NIPS.

Fitness Expectation Maximization

Tom Schaul, Jürgen Schmidhuber, Jan Peters, 2008, PPSN.

Efficient Natural Evolution Strategies Evolution Strategies and Evolutionary Programming Track

T. Schaul, Daan Wierstra, Yi Sun, 2009 .

Neural scene representation and rendering

Koray Kavukcuoglu, Daan Wierstra, Karol Gregor, 2018, Science.

Imagination-Augmented Agents for Deep Reinforcement Learning

Razvan Pascanu, Demis Hassabis, David Silver, 2017, NIPS.

Meta-Learning with Memory-Augmented Neural Networks

Daan Wierstra, Matthew Botvinick, Timothy P. Lillicrap, 2016, ICML.

DRAW: A Recurrent Neural Network For Image Generation pdf

Alex Graves, Daan Wierstra, Karol Gregor, 2015, ICML.

Solving Deep Memory POMDPs with Recurrent Policy Gradients

Jürgen Schmidhuber, Alexander Förster, Jan Peters, 2007, ICANN.

PathNet: Evolution Channels Gradient Descent in Super Neural Networks pdf

Chrisantha Fernando, Daan Wierstra, Charles Blundell, 2017, ArXiv.

One-shot Learning with Memory-Augmented Neural Networks pdf

Daan Wierstra, Matthew Botvinick, Timothy P. Lillicrap, 2016, ArXiv.

Recurrent policy gradients

Jürgen Schmidhuber, Alexander Förster, Jan Peters, 2010, Log. J. IGPL.

Variational Intrinsic Control pdf

Daan Wierstra, Karol Gregor, Danilo Jimenez Rezende, 2016, ICLR.

Stochastic Back-propagation and Variational Inference in Deep Latent Gaussian Models pdf

Daan Wierstra, Shakir Mohamed, Danilo Jimenez Rezende, 2014, ArXiv.

A System for Robotic Heart Surgery that Learns to Tie Knots Using Recurrent Neural Networks

Jürgen Schmidhuber, Alois Knoll, Faustino J. Gomez, 2006 .

Natural Evolution Strategies

Tom Schaul, Jan Peters, Daan Wierstra, 2008, 2008 IEEE Congress on Evolutionary Computation (IEEE World Congress on Computational Intelligence).

Towards Conceptual Compression

Daan Wierstra, Karol Gregor, Ivo Danihelka, 2016, NIPS.

Exploring parameter space in reinforcement learning

Tom Schaul, Yi Sun, Frank Sehnke, 2010, Paladyn J. Behav. Robotics.

Learning model-based planning from scratch pdf

Razvan Pascanu, Yujia Li, Oriol Vinyals, 2017, ArXiv.

Recurrent Environment Simulators pdf

Daan Wierstra, Shakir Mohamed, Silvia Chiappa, 2017, ICLR.

One-Shot Generalization in Deep Generative Models

Daan Wierstra, Karol Gregor, Ivo Danihelka, 2016, ICML.

Weight Uncertainty in Neural Network

Julien Cornebise, Koray Kavukcuoglu, Daan Wierstra, 2015, ICML.

Training Recurrent Networks by Evolino

Jürgen Schmidhuber, Faustino J. Gomez, Daan Wierstra, 2007, Neural Computation.

Exponential natural evolution strategies

Tom Schaul, Yi Sun, Jürgen Schmidhuber, 2010, GECCO '10.

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

Peter Dayan, Daan Wierstra, Benigno Uria, 2017, ArXiv.

Convolution by Evolution: Differentiable Pattern Producing Networks

David Pfau, Max Jaderberg, Chrisantha Fernando, 2016, GECCO.

Evolino: Hybrid Neuroevolution/Optimal Linear Search for Sequence Learning

Jürgen Schmidhuber, Faustino J. Gomez, Daan Wierstra, 2005, IJCAI.

Modeling systems with internal state using evolino

Jürgen Schmidhuber, Faustino J. Gomez, Daan Wierstra, 2005, GECCO '05.

A System for Robotic Heart Surgery that Learns to Tie Knots Using Recurrent Neural Networks

Jürgen Schmidhuber, Alois Knoll, Faustino J. Gomez, 2006, 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems.

Stochastic search using the natural gradient

Tom Schaul, Yi Sun, Jürgen Schmidhuber, 2009, ICML '09.

Building Machines that Learn and Think for Themselves: Commentary on Lake et al., Behavioral and Brain Sciences, 2017

Tom Schaul, Nando de Freitas, Shane Legg, 2017, 1711.08378.

Evolino for recurrent support vector machines pdf

Jürgen Schmidhuber, Faustino J. Gomez, Daan Wierstra, 2005, ESANN.

Evolving Memory Cell Structures for Sequence Learning

Julian Togelius, Jürgen Schmidhuber, Justin Bayer, 2009, ICANN.

Evolino: Hybrid Neuroevolution / Optimal Linear Search for Sequence Prediction

Jürgen Schmidhuber, Daan Wierstra, Faustino Gomez, 2005, IJCAI 2005.

Robust player imitation using multiobjective evolution

Julian Togelius, Jürgen Schmidhuber, Daan Wierstra, 2009, 2009 IEEE Congress on Evolutionary Computation.

Utile distinction hidden Markov models

Marco Wiering, Daan Wierstra, Daan Wierstra, 2004, ICML.

Variational Learning for Recurrent Spiking Networks

Wulfram Gerstner, Daan Wierstra, Danilo Jimenez Rezende, 2011, NIPS.

Recurrent Support Vector Machines

Faustino J. Gomez, J. Schmidhuber, Daan Wierstra, 2005 .

1 5 D ec 2 00 5 Evolino for Recurrent Support Vector Machines

Faustino J. Gomez, J. Schmidhuber, Daan Wierstra, 2022 .

Statistical Models for Non-markovian Control Tasks

Daan Wierstra, 2004 .

Algorithm 1 Curiosity-driven Optimization

J. Schmidhuber, T. Schaul, Daan Wierstra, 2011 .

S3TA: A Soft, Spatial, Sequential, Top-Down Attention Model

Alex Mott, Daan Wierstra, Mike Chrzanowski, 2018 .

Evolving Cell Structures for Sequence Learning

Julian Togelius, Jürgen Schmidhuber, Justin Bayer, 2009, ICANN 2009.

Leave Graphs Alone: Addressing Over-Squashing without Rewiring

George E. Dahl, N. Heess, Daan Wierstra, 2022 .

Unifying Grokking and Double Descent

Jessica B. Hamrick, George E. Dahl, Daan Wierstra, 2023, ArXiv.

PyBrain

T. Schaul, Daan Wierstra, Justin Bayer, 2010, J. Mach. Learn. Res..

A study in direct policy search

Daan Wierstra, Daan Wierstra, 2010 .

Policy Gradient Critics

Jürgen Schmidhuber, Daan Wierstra, J. Schmidhuber, 2007, ECML.

Curiosity-driven optimization

Tom Schaul, Yi Sun, Jürgen Schmidhuber, 2011, 2011 IEEE Congress of Evolutionary Computation (CEC).

Episodic Reinforcement Learning by Logistic Reward-Weighted Regression

Tom Schaul, Jürgen Schmidhuber, Jan Peters, 2008, ICANN.

Efficient natural evolution strategies

Tom Schaul, Yi Sun, Jürgen Schmidhuber, 2009, GECCO.

Deep AutoRegressive Networks pdf

Daan Wierstra, Charles Blundell, Karol Gregor, 2013, ICML.

Towards Interpretable Reinforcement Learning Using Attention Augmented Agents

Alex Mott, Daan Wierstra, Mike Chrzanowski, 2019, NeurIPS.

Learning and Querying Fast Generative Models for Reinforcement Learning pdf

Fabio Viola, Demis Hassabis, Daan Wierstra, 2018, ArXiv.

Leave Graphs Alone: Addressing Over-Squashing without Rewiring

George E. Dahl, N. Heess, Daan Wierstra, 2022, ArXiv.

Human-level control through deep reinforcement learning

Marc G. Bellemare, Martin A. Riedmiller, Andrei A. Rusu, 2015, Nature.

Relational inductive biases, deep learning, and graph networks

Jessica B. Hamrick, Kelsey R. Allen, George E. Dahl, 2018, ArXiv.

Ontogenetic and Phylogenetic Reinforcement Learning

Julian Togelius, Tom Schaul, Jürgen Schmidhuber, 2009, Künstliche Intell..

Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents

Diego Perez Liebana, William H. Guss, Alec Radford, 2022 .

Natural evolution strategies

SchmidhuberJürgen, PetersJan, SunYi, 2011, J. Mach. Learn. Res..