Search Results for author: Evangelos Theodorou

Found 17 papers, 1 papers with code

Safe Importance Sampling in Model Predictive Path Integral Control

no code implementations6 Mar 2023 Manan Gandhi, Hassan Almubarak, Evangelos Theodorou

We introduce the notion of importance sampling under embedded barrier state control, titled Safety Controlled Model Predictive Path Integral Control (SC-MPPI).

Safety in Augmented Importance Sampling: Performance Bounds for Robust MPPI

no code implementations12 Apr 2022 Manan Gandhi, Hassan Almubarak, Yuichiro Aoyama, Evangelos Theodorou

This work explores the nature of augmented importance sampling in safety-constrained model predictive control problems.

Model Predictive Control Motion Planning

Robustifying Reinforcement Learning Policies with $\mathcal{L}_1$ Adaptive Control

no code implementations4 Jun 2021 Yikun Cheng, Pan Zhao, Manan Gandhi, Bo Li, Evangelos Theodorou, Naira Hovakimyan

A reinforcement learning (RL) policy trained in a nominal environment could fail in a new/perturbed environment due to the existence of dynamic variations.

reinforcement-learning Reinforcement Learning (RL)

Exploring the representativeness of the M5 competition data

no code implementations4 Mar 2021 Evangelos Theodorou, Shengjie Wang, Yanfei Kang, Evangelos Spiliotis, Spyros Makridakis, Vassilios Assimakopoulos

The main objective of the M5 competition, which focused on forecasting the hierarchical unit sales of Walmart, was to evaluate the accuracy and uncertainty of forecasting methods in the field in order to identify best practices and highlight their practical implications.

Marketing Time Series +1

Multi-agent Deep FBSDE Representation For Large Scale Stochastic Differential Games

no code implementations28 Sep 2020 Tianrong Chen, Ziyi Wang, Ioannis Exarchos, Evangelos Theodorou

In this paper we present a deep learning framework for solving large-scale multi-agent non-cooperative stochastic games using fictitious play.

Decision Making

Contraction $\mathcal{L}_1$-Adaptive Control using Gaussian Processes

no code implementations8 Sep 2020 Aditya Gahlawat, Arun Lakshmanan, Lin Song, Andrew Patterson, Zhuohuan Wu, Naira Hovakimyan, Evangelos Theodorou

We present $\mathcal{CL}_1$-$\mathcal{GP}$, a control framework that enables safe simultaneous learning and control for systems subject to uncertainties.

Gaussian Processes

L1-GP: L1 Adaptive Control with Bayesian Learning

no code implementations L4DC 2020 Aditya Gahlawat, Pan Zhao, Andrew Patterson, Naira Hovakimyan, Evangelos Theodorou

We present L1-GP, an architecture based on L1 adaptive control and Gaussian Process Regression (GPR) for safe simultaneous control and learning.

GPR regression

Feynman-Kac Neural Network Architectures for Stochastic Control Using Second-Order FBSDE Theory

no code implementations L4DC 2020 Marcus Pereira, Ziyi Wang, Tianrong Chen, Emily Reed, Evangelos Theodorou

We present a deep recurrent neural network architecture to solve a class of stochastic optimal control problems described by fully nonlinear Hamilton Jacobi Bellman partial differential equations.

LEMMA

Deep Nonlinear Stochastic Optimal Control for Systems with Multiplicative Uncertainties

no code implementations25 Sep 2019 Marcus Pereira, Ziyi Wang, Tianrong Chen, Evangelos Theodorou

We present a deep recurrent neural network architecture to solve a class of stochastic optimal control problems described by fully nonlinear Hamilton Jacobi Bellman partial differential equations.

LEMMA

Propagating Uncertainty through the tanh Function with Application to Reservoir Computing

no code implementations25 Jun 2018 Manan Gandhi, Keuntaek Lee, Yunpeng Pan, Evangelos Theodorou

In this work, we contribute two new methods to propagate uncertainty through the tanh activation function and propose the Probabilistic Echo State Network (PESN), a method that is shown to have better average performance than deterministic Echo State Networks given the random initialization of reservoir states.

Model-Based Stochastic Search for Large Scale Optimization of Multi-Agent UAV Swarms

1 code implementation3 Mar 2018 David D. Fan, Evangelos Theodorou, John Reeder

Recent work from the reinforcement learning community has shown that Evolution Strategies are a fast and scalable alternative to other reinforcement learning methods.

Multiagent Systems

MPC-Inspired Neural Network Policies for Sequential Decision Making

no code implementations15 Feb 2018 Marcus Pereira, David D. Fan, Gabriel Nakajima An, Evangelos Theodorou

In this paper we investigate the use of MPC-inspired neural network policies for sequential decision making.

Decision Making

Imitation Learning for Agile Autonomous Driving

no code implementations21 Sep 2017 Yunpeng Pan, Ching-An Cheng, Kamil Saigol, Keuntaek Lee, Xinyan Yan, Evangelos Theodorou, Byron Boots

We present an end-to-end imitation learning system for agile, off-road autonomous driving using only low-cost on-board sensors.

Robotics

Sample Efficient Path Integral Control under Uncertainty

no code implementations NeurIPS 2015 Yunpeng Pan, Evangelos Theodorou, Michail Kontitsis

We present a data-driven stochastic optimal control framework that is derived using the path integral (PI) control approach.

Probabilistic Differential Dynamic Programming

no code implementations NeurIPS 2014 Yunpeng Pan, Evangelos Theodorou

We present a data-driven, probabilistic trajectory optimization framework for systems with unknown dynamics, called Probabilistic Differential Dynamic Programming (PDDP).

Gaussian Processes

Cannot find the paper you are looking for? You can Submit a new open access paper.