J
Jonas Buchli
Researcher at ETH Zurich
Publications - 166
Citations - 9460
Jonas Buchli is an academic researcher from ETH Zurich. The author has contributed to research in topics: Robot & Optimal control. The author has an hindex of 46, co-authored 164 publications receiving 7375 citations. Previous affiliations of Jonas Buchli include Istituto Italiano di Tecnologia & University of Southern California.
Papers
More filters
Journal Article
A Generalized Path Integral Control Approach to Reinforcement Learning
TL;DR: The framework of stochastic optimal control with path integrals is used to derive a novel approach to RL with parameterized policies to demonstrate interesting similarities with previous RL research in the framework of probability matching and provides intuition why the slightly heuristically motivated probability matching approach can actually perform well.
Erratum: A Generalized Path Integral Control Approach to Reinforcement Learning
TL;DR: In this paper, the authors correct a mistake in the derivation of the generalized path integral control in lemma 2 and show that the term b in equation (20) should not appear at all.
Journal ArticleDOI
Digital Concrete: Opportunities and Challenges
Timothy Wangler,Ena Lloret,Lex Reiter,Norman Hack,Fabio Gramazio,Matthias Kohler,Mathias Bernhard,Benjamin Dillenburger,Jonas Buchli,Nicolas Roussel,Robert J. Flatt +10 more
TL;DR: In this paper, the authors review the methods of digital fabrication with concrete, including 3D printing, under the encompassing term of digital concrete, identifying major challenges for concrete technology within this field.
Journal ArticleDOI
Gait and Trajectory Optimization for Legged Systems Through Phase-Based End-Effector Parameterization
TL;DR: A single trajectory optimization formulation for legged locomotion that automatically determines the gait sequence, step timings, footholds, swing-leg motions, and six-dimensional body motion over nonflat terrain, without any additional modules is presented.
Journal ArticleDOI
Dynamic hebbian learning in adaptive frequency oscillators
TL;DR: A learning rule for oscillators which adapts their frequency to the frequency of any periodic or pseudo-periodic input signal, which is easily generalizable to a large class of oscillators, from phase oscillators to relaxation oscillators and strange attractors with a generic learning rule.