Jonas Buchli
Artificial Intelligence · 2006–2022
A researcher in the Science corpus: 16 papers; trusts 72 researchers and is trusted by 142 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 131 citations into it; #3,608 of 36,961 by trust here, #11,794 by citations
- Control and Systems Engineering — 95 citations into it; #341 of 8,519 by trust here, #490 by citations
- Reinforcement Learning — 78 citations into it; #232 of 2,250 by trust here, #646 by citations
- Cognitive Neuroscience — 70 citations into it; #3,391 of 11,026 by trust here, #4,947 by citations
- Biomedical Engineering — 55 citations into it; #3,877 of 10,753 by trust here, #4,414 by citations
- Computer Vision and Pattern Recognition — 30 citations into it; #13,583 of 21,973 by trust here, #15,890 by citations
- Robotics & Control — 23 citations into it; #485 of 612 by trust here, #541 by citations
- Management Science and Operations Research — 21 citations into it; #1,330 of 12,201 by trust here, #2,758 by citations
Whom Jonas Buchli trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Jan Peters
- Stefan Schaal
- E. Todorov
- Richard S. Sutton
- Auke Jan Ijspeert
- Hilbert J. Kappen
- Jens Kober
- Bernt Øksendal
- Andrew Barto
- Evangelos A. Theodorou
Who trusts Jonas Buchli overall
- Sergey Levine
- Mrinal Kalakrishnan
- Pieter Abbeel
- Abhishek Gupta
- Freek Stulp
- Vikash Kumar
- Jan Peters
- Peter Pastor
- Auke Jan Ijspeert
- Yevgen Chebotar
Papers from Jonas Buchli's perspective
Ordered by how strongly the researchers Jonas Buchli trusts endorse each paper. Same corpus, a different order for every researcher.
- ImageNet classification with deep convolutional neural networks
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Reinforcement Learning: An Introduction
- Gradient-based learning applied to document recognition
- Long Short-Term Memory
- Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning
- ImageNet: A large-scale hierarchical image database
- Attention is All you Need (Neural Information Processing Systems)
- GENERATIVE ADVERSARIAL NETS
Their papers
- Reinforcement learning of motor skills in high dimensions: A path integral approach (2010) — 303 citations
- Shaking the foundations: delusions in sequence models for interaction and control (2021) — 75 citations
- Learning locomotion over rough terrain using terrain templates (2009) — 106 citations
- Learning to grasp under uncertainty (2011) — 98 citations
- Dynamical principles for neuroscience and intelligent biomimetic devices (2006) — 8 citations
- Why off-the-shelf physics simulators fail in evaluating feedback controller performance - a case study for quadrupedal robots (2016) — 29 citations
- Learning Policy Improvements with Path Integrals (2010) — 69 citations
- Learning variable impedance control (2011) — 397 citations
- A reactive controller framework for quadrupedal locomotion on challenging terrain (2013) — 199 citations
- Whole-Body Nonlinear Model Predictive Control Through Contacts for Quadrupeds (2017) — 303 citations
- Learning, planning, and control for quadruped locomotion over challenging terrain (2011) — 342 citations
- Gait and Trajectory Optimization for Legged Systems Through Phase-Based End-Effector Parameterization (2018) — 484 citations
- Magnetic control of tokamak plasmas through deep reinforcement learning (2022) — 923 citations
- Digital Concrete: Opportunities and Challenges (2016) — 562 citations
- A Generalized Path Integral Control Approach to Reinforcement Learning (2010) — 700 citations
- Dynamic hebbian learning in adaptive frequency oscillators (2006) — 401 citations