H-Index & Metrics Best Publications

H-Index & Metrics

Discipline name H-index Citations Publications World Ranking National Ranking
Computer Science D-index 44 Citations 22,520 109 World Ranking 3738 National Ranking 1903

Overview

What is he best known for?

The fields of study he is best known for:

  • Artificial intelligence
  • Machine learning
  • Programming language

Nicolas Heess mainly focuses on Artificial intelligence, Reinforcement learning, Control, Set and Machine learning. His Artificial intelligence research includes themes of Structure and Computation. His Reinforcement learning research is multidisciplinary, incorporating elements of Domain, Robot, Image resolution and Contextual image classification.

His Control study integrates concerns from other disciplines, such as Backpropagation and Scratch. The study incorporates disciplines such as Embedding, Parameterized complexity, Latent variable and Human–computer interaction in addition to Set. His biological study deals with issues like Generative grammar, which deal with fields such as Unsupervised learning and Visual structure.

His most cited work include:

  • Continuous control with deep reinforcement learning (3189 citations)
  • Deterministic Policy Gradient Algorithms (1413 citations)
  • Continuous control with deep reinforcement learning (1200 citations)

What are the main themes of his work throughout his whole career to date?

Nicolas Heess mainly investigates Reinforcement learning, Artificial intelligence, Machine learning, Mathematical optimization and Control. The various areas that Nicolas Heess examines in his Reinforcement learning study include Domain, Theoretical computer science, Human–computer interaction, Set and Range. He works mostly in the field of Human–computer interaction, limiting it down to concerns involving Control theory and, occasionally, Robotic arm.

Artificial intelligence is closely attributed to Structure in his study. Nicolas Heess studied Mathematical optimization and Kullback–Leibler divergence that intersect with Algorithm. As a part of the same scientific study, he usually deals with the Control, concentrating on Value and frequently concerns with Hindsight bias.

He most often published in these fields:

  • Reinforcement learning (60.67%)
  • Artificial intelligence (55.06%)
  • Machine learning (20.79%)

What were the highlights of his more recent work (between 2020-2021)?

  • Reinforcement learning (60.67%)
  • Mathematical optimization (15.17%)
  • Artificial intelligence (55.06%)

In recent papers he was focusing on the following fields of study:

His scientific interests lie mostly in Reinforcement learning, Mathematical optimization, Artificial intelligence, Hindsight bias and Key. His Reinforcement learning research includes elements of Latent variable, Bellman equation, Intelligent agent, Dynamic programming and Robustness. His Robustness research is multidisciplinary, incorporating perspectives in Domain, Control, Shape space and Software deployment.

His biological study spans a wide range of topics, including Function, Measure, Value and Exploration problem. When carried out as part of a general Artificial intelligence research project, his work on Object is frequently linked to work in Simple, therefore connecting diverse disciplines of study. His Hindsight bias study combines topics in areas such as Backpropagation, Mathematical economics and Inference.

Between 2020 and 2021, his most popular works were:

  • Action and Perception as Divergence Minimization (9 citations)
  • Data-efficient Hindsight Off-policy Option Learning (3 citations)
  • Robust Constrained Reinforcement Learning for Continuous Control with Model Misspecification (2 citations)

In his most recent research, the most cited papers focused on:

  • Artificial intelligence
  • Machine learning
  • Programming language

Nicolas Heess focuses on Reinforcement learning, Machine learning, Artificial intelligence, Robustness and Mathematical optimization. His Reinforcement learning study incorporates themes from Latent variable model and Robot. The concepts of his Latent variable model study are interwoven with issues in Intelligent agent, Mutual information and Feature learning.

His Robot research integrates issues from Hindsight bias, Backpropagation, Dynamic programming and Inference. The Robustness study combines topics in areas such as Domain, Control and Software deployment.

This overview was generated by a machine learning system which analysed the scientist’s body of work. If you have any feedback, you can contact us here.

Best Publications

Continuous control with deep reinforcement learning

Timothy P. Lillicrap;Jonathan J. Hunt;Alexander Pritzel;Nicolas Heess.
arXiv: Learning (2015)

3930 Citations

Deterministic Policy Gradient Algorithms

David Silver;Guy Lever;Nicolas Heess;Thomas Degris.
international conference on machine learning (2014)

2056 Citations

Recurrent Models of Visual Attention

Volodymyr Mnih;Nicolas Heess;Alex Graves;koray kavukcuoglu.
neural information processing systems (2014)

1163 Citations

Relational inductive biases, deep learning, and graph networks

Peter W. Battaglia;Jessica B. Hamrick;Victor Bapst;Alvaro Sanchez-Gonzalez.
arXiv: Learning (2018)

873 Citations

Emergence of Locomotion Behaviours in Rich Environments

Nicolas Heess;Dhruva Tb;Srinivasan Sriram;Jay Lemmon.
arXiv: Artificial Intelligence (2017)

557 Citations

Learning generative texture models with extended Fields-of-Experts

Nicolas Heess;Christopher K. I. Williams;Geoffrey E. Hinton.
british machine vision conference (2009)

438 Citations

Leveraging Demonstrations for Deep Reinforcement Learning on Robotics Problems with Sparse Rewards

Matej Vecerík;Todd Hester;Jonathan Scholz;Fumin Wang.
arXiv: Artificial Intelligence (2017)

349 Citations

Learning continuous control policies by stochastic value gradients

Nicolas Heess;Greg Wayne;David Silver;Timothy Lillicrap.
neural information processing systems (2015)

279 Citations

FeUdal Networks for Hierarchical Reinforcement Learning

Alexander Sasha Vezhnevets;Simon Osindero;Tom Schaul;Nicolas Heess.
arXiv: Artificial Intelligence (2017)

276 Citations

The Shape Boltzmann Machine: A Strong Model of Object Shape

S. M. Eslami;Nicolas Heess;Christopher K. Williams;John Winn.
International Journal of Computer Vision (2014)

236 Citations

If you think any of the details on this page are incorrect, let us know.

Contact us

Best Scientists Citing Nicolas Heess

Sergey Levine

Sergey Levine

University of California, Berkeley

Publications: 202

Pieter Abbeel

Pieter Abbeel

University of California, Berkeley

Publications: 116

Jan Peters

Jan Peters

TU Darmstadt

Publications: 53

Chelsea Finn

Chelsea Finn

Google (United States)

Publications: 53

Shimon Whiteson

Shimon Whiteson

University of Oxford

Publications: 49

Joshua B. Tenenbaum

Joshua B. Tenenbaum

MIT

Publications: 44

Silvio Savarese

Silvio Savarese

Stanford University

Publications: 42

Pushmeet Kohli

Pushmeet Kohli

Google (United States)

Publications: 38

Ruslan Salakhutdinov

Ruslan Salakhutdinov

Carnegie Mellon University

Publications: 38

Yoshua Bengio

Yoshua Bengio

University of Montreal

Publications: 37

Honglak Lee

Honglak Lee

University of Michigan–Ann Arbor

Publications: 33

Li Fei-Fei

Li Fei-Fei

Stanford University

Publications: 33

Jitendra Malik

Jitendra Malik

University of California, Berkeley

Publications: 32

Trevor Darrell

Trevor Darrell

University of California, Berkeley

Publications: 31

Jiajun Wu

Jiajun Wu

Stanford University

Publications: 30

Joelle Pineau

Joelle Pineau

Facebook (United States)

Publications: 30

Something went wrong. Please try again later.