Volodymyr Mnih

发表

Modeling Natural Images Using Gated MRFs

Geoffrey E. Hinton, Marc'Aurelio Ranzato, Volodymyr Mnih, 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

CUDAMat: a CUDA-based matrix class for Python

Volodymyr Mnih, Volodymyr Mnih, 2009 .

Machine Learning for Aerial Image Labeling

Geoffrey E. Hinton, Volodymyr Mnih, Volodymyr Mnih, 2013 .

Policy Distillation pdf

Razvan Pascanu, Sergio Gomez Colmenarejo, Raia Hadsell, 2015, ICLR.

Topological map learning from outdoor image sequences

Richard S. Zemel, Xuming He, Volodymyr Mnih, 2006, J. Field Robotics.

Unsupervised Learning of Object Keypoints for Perception and Control

Ankush Gupta, Andrew Zisserman, Volodymyr Mnih, 2019, NeurIPS.

Reinforcement Learning with Unsupervised Auxiliary Tasks pdf

Tom Schaul, Joel Z. Leibo, Max Jaderberg, 2016, ICLR.

Multiple Object Recognition with Visual Attention pdf

Koray Kavukcuoglu, Jimmy Ba, Volodymyr Mnih, 2014, ICLR.

PGQ: Combining policy gradient and Q-learning pdf

Koray Kavukcuoglu, Brendan O'Donoghue, Volodymyr Mnih, 2016, ArXiv.

Human-level control through deep reinforcement learning

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

Fast Task Inference with Variational Intrinsic Successor Features pdf

David Warde-Farley, Volodymyr Mnih, André Barreto, 2019, ICLR.

Learning to Detect Roads in High-Resolution Aerial Images

Geoffrey E. Hinton, Volodymyr Mnih, Volodymyr Mnih, 2010, ECCV.

Sample Efficient Actor-Critic with Experience Replay pdf

Nando de Freitas, Rémi Munos, Koray Kavukcuoglu, 2016, ICLR.

Conditional Restricted Boltzmann Machines for Structured Output Prediction

Geoffrey E. Hinton, Hugo Larochelle, Volodymyr Mnih, 2011, UAI.

Combining policy gradient and Q-learning

Koray Kavukcuoglu, Brendan O'Donoghue, Volodymyr Mnih, 2016, ICLR.

The Uncertainty Bellman Equation and Exploration

Ian Osband, Brendan O'Donoghue, Volodymyr Mnih, 2017, ICML.

Relative Variational Intrinsic Control pdf

David Warde-Farley, Volodymyr Mnih, Steven Hansen, 2020, ArXiv.

Learning by Playing - Solving Sparse Reward Tasks from Scratch

Martin A. Riedmiller, Thomas Lampe, Jost Tobias Springenberg, 2018, ICML.

Learning values across many orders of magnitude

David Silver, Matteo Hessel, Arthur Guez, 2016, NIPS.

IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures pdf

Shane Legg, Rémi Munos, Iain Dunning, 2018, ICML.

Unsupervised Control Through Non-Parametric Discriminative Rewards pdf

David Warde-Farley, Volodymyr Mnih, Tejas D. Kulkarni, 2018, ICLR.

Using Fast Weights to Attend to the Recent Past

Geoffrey E. Hinton, Joel Z. Leibo, Jimmy Ba, 2016, NIPS.

Asynchronous Methods for Deep Reinforcement Learning pdf

Alex Graves, Koray Kavukcuoglu, David Silver, 2016, ICML.

On deep generative models with applications to recognition

Geoffrey E. Hinton, Marc'Aurelio Ranzato, Volodymyr Mnih, 2011, CVPR 2011.

Learning to Label Aerial Images from Noisy Data

Geoffrey E. Hinton, Volodymyr Mnih, Volodymyr Mnih, 2012, ICML.

Playing Atari with Deep Reinforcement Learning pdf

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

Q-Learning in enormous action spaces via amortized approximate maximization pdf

Andriy Mnih, David Warde-Farley, Volodymyr Mnih, 2020, ArXiv.

Massively Parallel Methods for Deep Reinforcement Learning pdf

Shane Legg, Praveen Srinivasan, Koray Kavukcuoglu, 2015, ArXiv.

Strategic Attentive Writer for Learning Macro-Actions

Alex Graves, Simon Osindero, Koray Kavukcuoglu, 2016, NIPS.

Empirical Bernstein stopping

Csaba Szepesvári, Volodymyr Mnih, Jean-Yves Audibert, 2008, ICML '08.

Generating more realistic images using gated MRF's

Geoffrey E. Hinton, Marc'Aurelio Ranzato, Volodymyr Mnih, 2010, NIPS.

Recurrent Models of Visual Attention

Alex Graves, Koray Kavukcuoglu, Nicolas Heess, 2014, NIPS.

Relative Variational Intrinsic Control

David Warde-Farley, Volodymyr Mnih, Kate Baumli, 2020, AAAI.

Wasserstein Distance Maximizing Intrinsic Control pdf

Ishan Durugkar, Volodymyr Mnih, Steven Hansen, 2021, ArXiv.

Discovering Diverse Nearly Optimal Policies withSuccessor Features pdf

Brendan O'Donoghue, Tom Zahavy, Volodymyr Mnih, 2021, ArXiv.