H-Index & Metrics Top Publications

H-Index & Metrics

Discipline name H-index Citations Publications World Ranking National Ranking
Computer Science H-index 76 Citations 26,428 386 World Ranking 549 National Ranking 22

Overview

What is he best known for?

The fields of study he is best known for:

  • Artificial intelligence
  • Machine learning
  • Statistics

His primary scientific interests are in Artificial intelligence, Reinforcement learning, Robot, Robot learning and Machine learning. His Artificial intelligence study frequently draws connections to other fields, such as Motor skill. His studies in Reinforcement learning integrate themes in fields like Active learning, Mathematical optimization, Bellman equation, Stability and Imitation.

Jan Peters interconnects Trajectory, Table, Computer vision and GRASP in the investigation of issues within Robot. He focuses mostly in the field of Robot learning, narrowing it down to topics relating to Multi-task learning and, in certain cases, Instance-based learning and Semi-supervised learning. His Machine learning course of study focuses on Probabilistic logic and Human–robot interaction.

His most cited work include:

  • Reinforcement learning in robotics: A survey (1428 citations)
  • 2008 Special Issue: Reinforcement learning of motor skills with policy gradients (624 citations)
  • A Survey on Policy Search for Robotics (575 citations)

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

Artificial intelligence, Robot, Reinforcement learning, Machine learning and Robotics are his primary areas of study. His Artificial intelligence research integrates issues from Motor skill and Computer vision. In his research, Social robot is intimately related to Human–computer interaction, which falls under the overarching field of Robot.

His Reinforcement learning research focuses on Mathematical optimization and how it connects with Markov decision process. His study in Online machine learning, Semi-supervised learning and Unsupervised learning falls within the category of Machine learning. His Robot learning study integrates concerns from other disciplines, such as Multi-task learning and Active learning, Instance-based learning.

He most often published in these fields:

  • Artificial intelligence (57.30%)
  • Robot (43.39%)
  • Reinforcement learning (29.89%)

What were the highlights of his more recent work (between 2019-2021)?

  • Artificial intelligence (57.30%)
  • Robot (43.39%)
  • Reinforcement learning (29.89%)

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

His main research concerns Artificial intelligence, Robot, Reinforcement learning, Human–computer interaction and Robotics. His research in Artificial intelligence tackles topics such as Machine learning which are related to areas like Task analysis. Jan Peters has included themes like GRASP, Stability, Object, Computer vision and Key in his Robot study.

As a part of the same scientific family, he mostly works in the field of Reinforcement learning, focusing on Bellman equation and, on occasion, Nonparametric statistics. His work carried out in the field of Human–computer interaction brings together such families of science as Handshaking, Human–robot interaction and Social robot. The study incorporates disciplines such as Movement and Trajectory in addition to Probabilistic logic.

Between 2019 and 2021, his most popular works were:

  • Sharing Knowledge in Multi-Task Deep Reinforcement Learning (24 citations)
  • Dopaminergic modulation of the exploration/exploitation trade-off in human decision-making (13 citations)
  • Dopaminergic modulation of the exploration/exploitation trade-off in human decision-making (13 citations)

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

  • Artificial intelligence
  • Statistics
  • Machine learning

Jan Peters focuses on Artificial intelligence, Robot, Reinforcement learning, Haloperidol and Dopamine. His study in Artificial intelligence is interdisciplinary in nature, drawing from both Stability and Machine learning. His studies in Robot integrate themes in fields like Key, Human–computer interaction and Computer vision.

His Reinforcement learning study combines topics in areas such as Bellman equation, Robot learning, Robot control and Sample. In his study, Representation is inextricably linked to SIGNAL, which falls within the broad field of Robot learning. The various areas that Jan Peters examines in his Haloperidol study include Cognition, Dopaminergic modulation and Temporal discounting.

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.

Top Publications

Reinforcement learning in robotics: A survey

Jens Kober;J. Andrew Bagnell;Jan Peters.
The International Journal of Robotics Research (2013)

1715 Citations

Natural actor-critic

Jan Peters;Sethu Vijayakumar;Stefan Schaal.
european conference on machine learning (2005)

971 Citations

Natural Actor-Critic

Jan Peters;Stefan Schaal.
Neurocomputing (2008)

937 Citations

2008 Special Issue: Reinforcement learning of motor skills with policy gradients

Jan Peters;Stefan Schaal.
Neural Networks (2008)

854 Citations

Episodic future thinking reduces reward delay discounting through an enhancement of prefrontal-mediotemporal interactions.

Jan Peters;Christian Büchel.
Neuron (2010)

779 Citations

A Survey on Policy Search for Robotics

Marc Peter Deisenroth;Gerhard Neumann;Jan Peters.
(2013)

724 Citations

Policy search for motor primitives in robotics

Jens Kober;Jan Peters.
Machine Learning (2011)

645 Citations

Policy Gradient Methods for Robotics

Jan Peters;Stefan Schaal.
intelligent robots and systems (2006)

528 Citations

Relative entropy policy search

Jan Peters;Katharina Mülling;Yasemin Altün.
national conference on artificial intelligence (2010)

475 Citations

The neural mechanisms of inter-temporal decision-making: understanding variability

Jan Peters;Christian Büchel.
Trends in Cognitive Sciences (2011)

448 Citations

Profile was last updated on December 6th, 2021.
Research.com Ranking is based on data retrieved from the Microsoft Academic Graph (MAG).
The ranking h-index is inferred from publications deemed to belong to the considered discipline.

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

Contact us

Top Scientists Citing Jan Peters

Sergey Levine

Sergey Levine

University of California, Berkeley

Publications: 165

Pieter Abbeel

Pieter Abbeel

University of California, Berkeley

Publications: 108

Stefan Schaal

Stefan Schaal

University of Southern California

Publications: 94

Ales Ude

Ales Ude

Jožef Stefan Institute

Publications: 72

Sylvain Calinon

Sylvain Calinon

Idiap Research Institute

Publications: 60

Jürgen Schmidhuber

Jürgen Schmidhuber

Dalle Molle Institute for Artificial Intelligence Research

Publications: 52

Darwin G. Caldwell

Darwin G. Caldwell

Italian Institute of Technology

Publications: 51

Marc Toussaint

Marc Toussaint

Max Planck Society

Publications: 50

Danica Kragic

Danica Kragic

Royal Institute of Technology

Publications: 50

Evangelos A. Theodorou

Evangelos A. Theodorou

Georgia Institute of Technology

Publications: 45

Masashi Sugiyama

Masashi Sugiyama

University of Tokyo

Publications: 45

Aude Billard

Aude Billard

École Polytechnique Fédérale de Lausanne

Publications: 44

Warren K. Bickel

Warren K. Bickel

Virginia Tech

Publications: 43

Jun Morimoto

Jun Morimoto

Kyoto University

Publications: 40

Hugh Garavan

Hugh Garavan

University of Vermont

Publications: 40

Something went wrong. Please try again later.