E
Evangelos A. Theodorou
Researcher at Georgia Institute of Technology
Publications - 269
Citations - 7931
Evangelos A. Theodorou is an academic researcher from Georgia Institute of Technology. The author has contributed to research in topics: Optimal control & Stochastic control. The author has an hindex of 36, co-authored 237 publications receiving 6022 citations. Previous affiliations of Evangelos A. Theodorou include University of Southern California & University of Washington.
Papers
More filters
Proceedings ArticleDOI
STOMP: Stochastic trajectory optimization for motion planning
TL;DR: It is experimentally show that the stochastic nature of STOMP allows it to overcome local minima that gradient-based methods like CHOMP can get stuck in.
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.
Proceedings ArticleDOI
Information theoretic MPC for model-based reinforcement learning
Grady Williams,Nolan Wagener,Brian Goldfain,Paul Drews,James M. Rehg,Byron Boots,Evangelos A. Theodorou +6 more
TL;DR: An information theoretic model predictive control algorithm capable of handling complex cost criteria and general nonlinear dynamics and using multi-layer neural networks as dynamics models to solve model-based reinforcement learning tasks is introduced.
Proceedings ArticleDOI
Aggressive driving with model predictive path integral control
TL;DR: A model predictive control algorithm designed for optimizing non-linear systems subject to complex cost criteria using a stochastic optimal control framework using a fundamental relationship between the information theoretic notions of free energy and relative entropy is presented.