Search Results for author: Evangelos A. Theodorou

Found 36 papers, 5 papers with code

Deep Graphic FBSDEs for Opinion Dynamics Stochastic Control

no code implementations5 Apr 2022 Tianrong Chen, Ziyi Wang, Evangelos A. Theodorou

Our approach relies on the probabilistic representation of the solution of the Hamilton-Jacobi-Bellman partial differential equation.

Decentralized Safe Multi-agent Stochastic Optimal Control using Deep FBSDEs and ADMM

no code implementations22 Feb 2022 Marcus A. Pereira, Augustinos D. Saravanos, Oswin So, Evangelos A. Theodorou

In this work, we propose a novel safe and scalable decentralized solution for multi-agent control in the presence of stochastic disturbances.

Barrier States Embedded Iterative Dynamic Game for Robust and Safe Trajectory Optimization

no code implementations4 Nov 2021 Hassan Almubarak, Evangelos A. Theodorou, Nader Sadegh

The proposed method leverages a game theoretic differential dynamic programming approach with barrier states to handle parametric and non-parametric uncertainties in safety-critical control systems.

Decision Making

Likelihood Training of Schrödinger Bridge using Forward-Backward SDEs Theory

1 code implementation ICLR 2022 Tianrong Chen, Guan-Horng Liu, Evangelos A. Theodorou

However, it remains unclear whether the optimization principle of SB relates to the modern training of deep generative models, which often rely on constructing log-likelihood objectives. This raises questions on the suitability of SB models as a principled alternative for generative applications.

Image Generation

Second-Order Neural ODE Optimizer

1 code implementation NeurIPS 2021 Guan-Horng Liu, Tianrong Chen, Evangelos A. Theodorou

We propose a novel second-order optimization framework for training the emerging deep continuous-time models, specifically the Neural Ordinary Differential Equations (Neural ODEs).

Image Classification Second-order methods +2

Generalization of Safe Optimal Control Actions on Networked Multi-Agent Systems

no code implementations21 Sep 2021 Lin Song, Neng Wan, Aditya Gahlawat, Chuyuan Tao, Naira Hovakimyan, Evangelos A. Theodorou

The control action composition is achieved by taking a weighted mixture of the existing controllers according to the contribution of each component task.

Deep $\mathcal{L}^1$ Stochastic Optimal Control Policies for Planetary Soft-landing

no code implementations1 Sep 2021 Marcus A. Pereira, Camilo A. Duarte, Ioannis Exarchos, Evangelos A. Theodorou

In this paper, we introduce a novel deep learning based solution to the Powered-Descent Guidance (PDG) problem, grounded in principles of nonlinear Stochastic Optimal Control (SOC) and Feynman-Kac theory.

Learning Risk-aware Costmaps for Traversability in Challenging Environments

no code implementations25 Jul 2021 David D. Fan, Ali-akbar Agha-mohammadi, Evangelos A. Theodorou

One of the main challenges in autonomous robotic exploration and navigation in unknown and unstructured environments is determining where the robot can or cannot safely move.

HJB Based Optimal Safe Control Using Control Barrier Functions

no code implementations29 Jun 2021 Hassan Almubarak, Evangelos A. Theodorou, Nader Sadegh

This work proposes an optimal safe controller minimizing an infinite horizon cost functional subject to control barrier functions (CBFs) safety conditions.

Dynamic Game Theoretic Neural Optimizer

no code implementations8 May 2021 Guan-Horng Liu, Tianrong Chen, Evangelos A. Theodorou

The connection between training deep neural networks (DNNs) and optimal control theory (OCT) has attracted considerable attention as a principled tool of algorithmic design.

Image Classification

Variational Inference MPC using Tsallis Divergence

no code implementations1 Apr 2021 Ziyi Wang, Oswin So, Jason Gibson, Bogdan Vlahov, Manan S. Gandhi, Guan-Horng Liu, Evangelos A. Theodorou

In this paper, we provide a generalized framework for Variational Inference-Stochastic Optimal Control by using thenon-extensive Tsallis divergence.

Variational Inference

Safety Embedded Control of Nonlinear Systems via Barrier States

no code implementations20 Feb 2021 Hassan Almubarak, Nader Sadegh, Evangelos A. Theodorou

The development enforces safety by means of barrier functions used in optimization through the construction of barrier states (BaS) which are embedded in the control system's model.

Distributed Algorithms for Linearly-Solvable Optimal Control in Networked Multi-Agent Systems

no code implementations18 Feb 2021 Neng Wan, Aditya Gahlawat, Naira Hovakimyan, Evangelos A. Theodorou, Petros G. Voulgaris

Distributed algorithms for both discrete-time and continuous-time linearly solvable optimal control (LSOC) problems of networked multi-agent systems (MASs) are investigated in this paper.

Large-Scale Multi-Agent Deep FBSDEs

no code implementations21 Nov 2020 Tianrong Chen, Ziyi Wang, Ioannis Exarchos, Evangelos A. Theodorou

We showcase superior performance of our framework over the state-of-the-art deep fictitious play algorithm on an inter-bank lending/borrowing problem in terms of multiple metrics.

Decision Making

Cooperative Path Integral Control for Stochastic Multi-Agent Systems

no code implementations30 Sep 2020 Neng Wan, Aditya Gahlawat, Naira Hovakimyan, Evangelos A. Theodorou, Petros G. Voulgaris

Local control actions that rely only on agents' local observations are designed to optimize the joint cost functions of subsystems.

Compositionality of Linearly Solvable Optimal Control in Networked Multi-Agent Systems

no code implementations28 Sep 2020 Lin Song, Neng Wan, Aditya Gahlawat, Naira Hovakimyan, Evangelos A. Theodorou

The proposed approach achieves both the compositionality and optimality of control actions simultaneously within the cooperative MAS framework in both discrete- and continuous-time in a sample-efficient manner, which reduces the burden of re-computation of the optimal control solutions for the new task on the MASs.

Safe Optimal Control Using Stochastic Barrier Functions and Deep Forward-Backward SDEs

no code implementations2 Sep 2020 Marcus Aloysius Pereira, Ziyi Wang, Ioannis Exarchos, Evangelos A. Theodorou

This paper introduces a new formulation for stochastic optimal control and stochastic dynamic optimization that ensures safety with respect to state and control constraints.

Adaptive Risk Sensitive Model Predictive Control with Stochastic Search

no code implementations2 Sep 2020 Ziyi Wang, Oswin So, Keuntaek Lee, Camilo A. Duarte, Evangelos A. Theodorou

We present a general framework for optimizing the Conditional Value-at-Risk for dynamical systems using stochastic search.

Distributional Reinforcement Learning Optimization and Control Robotics

A Differential Game Theoretic Neural Optimizer for Training Residual Networks

no code implementations17 Jul 2020 Guan-Horng Liu, Tianrong Chen, Evangelos A. Theodorou

Connections between Deep Neural Networks (DNNs) training and optimal control theory has attracted considerable attention as a principled tool of algorithmic design.

Image Classification

NOVAS: Non-convex Optimization via Adaptive Stochastic Search for End-to-End Learning and Control

no code implementations ICLR 2021 Ioannis Exarchos, Marcus A. Pereira, Ziyi Wang, Evangelos A. Theodorou

In this work we propose the use of adaptive stochastic search as a building block for general, non-convex optimization operations within deep neural network architectures.

Structured Prediction

DDPNOpt: Differential Dynamic Programming Neural Optimizer

no code implementations ICLR 2021 Guan-Horng Liu, Tianrong Chen, Evangelos A. Theodorou

Interpretation of Deep Neural Networks (DNNs) training as an optimal control problem with nonlinear dynamical systems has received considerable attention recently, yet the algorithmic development remains relatively limited.

Second-order methods

Deep Learning Tubes for Tube MPC

no code implementations5 Feb 2020 David D. Fan, Ali-akbar Agha-mohammadi, Evangelos A. Theodorou

This uncertainty may come from errors in learning (due to a lack of data, for example), or may be inherent to the system.

Model-based Reinforcement Learning

Bayesian Learning-Based Adaptive Control for Safety Critical Systems

2 code implementations5 Oct 2019 David D. Fan, Jennifer Nguyen, Rohan Thakker, Nikhilesh Alatur, Ali-akbar Agha-mohammadi, Evangelos A. Theodorou

We propose a framework which satisfies these constraints while allowing the use of deep neural networks for learning model uncertainties.

Autonomous Vehicles Bayesian Inference +2

Deep Learning Theory Review: An Optimal Control and Dynamical Systems Perspective

1 code implementation28 Aug 2019 Guan-Horng Liu, Evangelos A. Theodorou

In this article, we provide one possible way to align existing branches of deep learning theory through the lens of dynamical system and optimal control.

Learning Theory Meta-Learning

Deep Forward-Backward SDEs for Min-max Control

no code implementations11 Jun 2019 Ziyi Wang, Keuntaek Lee, Marcus A. Pereira, Ioannis Exarchos, Evangelos A. Theodorou

This paper presents a novel approach to numerically solve stochastic differential games for nonlinear systems.

Deep 2FBSDEs For Systems With Control Multiplicative Noise

no code implementations11 Jun 2019 Marcus A. Pereira, Ziyi Wang, Tianrong Chen, Emily Reed, Evangelos A. Theodorou

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

Perceptual Attention-based Predictive Control

no code implementations26 Apr 2019 Keuntaek Lee, Gabriel Nakajima An, Viacheslav Zakharov, Evangelos A. Theodorou

The proposed information processing architecture is used to support a perceptual attention-based predictive control algorithm that leverages model predictive control (MPC), convolutional neural networks (CNNs), and uncertainty quantification methods.

Visual Navigation

Accelerating Imitation Learning with Predictive Models

no code implementations12 Jun 2018 Ching-An Cheng, Xinyan Yan, Evangelos A. Theodorou, Byron Boots

When the model oracle is learned online, these algorithms can provably accelerate the best known convergence rate up to an order.

Imitation Learning

Safe end-to-end imitation learning for model predictive control

no code implementations27 Mar 2018 Keuntaek Lee, Kamil Saigol, Evangelos A. Theodorou

We propose the use of Bayesian networks, which provide both a mean value and an uncertainty estimate as output, to enhance the safety of learned control policies under circumstances in which a test-time input differs significantly from the training set.

Autonomous Driving Imitation Learning

Safe Learning of Quadrotor Dynamics Using Barrier Certificates

no code implementations16 Oct 2017 Li Wang, Evangelos A. Theodorou, Magnus Egerstedt

The barrier certificates establish a non-conservative forward invariant safe region, in which high probability safety guarantees are provided based on the statistics of the Gaussian Process.

Gaussian Processes

Information Theoretic Model Predictive Control: Theory and Applications to Autonomous Driving

2 code implementations7 Jul 2017 Grady Williams, Paul Drews, Brian Goldfain, James M. Rehg, Evangelos A. Theodorou

We present an information theoretic approach to stochastic optimal control problems that can be used to derive general sampling based optimization schemes.

Robotics

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