31 citations · 84 across the 12 of their papers we have counts for
12 papers
Solving Inverse Problems via Diffusion Optimal Control
Henry Li, Marcus Pereira
Existing approaches to diffusion-based inverse problem solvers frame the signal recovery task as a probabilistic sampling episode, where the solution is drawn from the desired post…
Decentralized Safe Multi-agent Stochastic Optimal Control using Deep FBSDEs and ADMM
Marcus A. Pereira, Augustinos D. Saravanos, Oswin So +1
In this work, we propose a novel safe and scalable decentralized solution for multi-agent control in the presence of stochastic disturbances. Safety is mathematically encoded using…
Deep Stochastic Optimal Control Policies for Planetary Soft-landing
Marcus A. Pereira, Camilo A. Duarte, Ioannis Exarchos +1
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)…
Safe Optimal Control Using Stochastic Barrier Functions and Deep Forward-Backward SDEs
Marcus Aloysius Pereira, Ziyi Wang, Ioannis Exarchos +1
This paper introduces a new formulation for stochastic optimal control and stochastic dynamic optimization that ensures safety with respect to state and control constraints. The pr…
NOVAS: Non-convex Optimization via Adaptive Stochastic Search for End-to-End Learning and Control
Ioannis Exarchos, Marcus A. Pereira, Ziyi Wang +1
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. Specific…
Variational Optimization Based Reinforcement Learning for Infinite Dimensional Stochastic Systems
Ethan N. Evans, Marcus A. Pereira, George I. Boutselis +1
Systems involving Partial Differential Equations (PDEs) have recently become more popular among the machine learning community. However prior methods usually treat infinite dimensi…
Deep Forward-Backward SDEs for Min-max Control
Ziyi Wang, Keuntaek Lee, Marcus A. Pereira +2
This paper presents a novel approach to numerically solve stochastic differential games for nonlinear systems. The proposed approach relies on the nonlinear Feynman-Kac theorem tha…
Deep 2FBSDEs For Systems With Control Multiplicative Noise
Marcus A Pereira, Ziyi Wang, Tianrong Chen +2
We present a deep recurrent neural network architecture to solve a class of stochastic optimal control problems described by fully nonlinear Hamilton Jacobi Bellmanpartial differen…
Leveraging Stochasticity for Open Loop and Model Predictive Control of Complex Fluid Systems
George I. Boutselis, Ethan N. Evans, Marcus A. Pereira +1
Stochastic Spatio-Temporal processes are prevalent across domains ranging from modeling of plasma to the turbulence in fluids to the wave function of quantum systems. This letter s…
Learning Deep Stochastic Optimal Control Policies using Forward-Backward SDEs
Marcus Pereira, Ziyi Wang, Ioannis Exarchos +1
In this paper we propose a new methodology for decision-making under uncertainty using recent advancements in the areas of nonlinear stochastic optimal control theory, applied math…
Variational Inference for Stochastic Control of Infinite Dimensional Systems
George I. Boutselis, Marcus Pereira, Evangelos A. Theodorou
This paper develops a variational inference framework for control of infinite dimensional stochastic systems. We employ a measure theoretic approach which relies on the generalizat…
MPC-Inspired Neural Network Policies for Sequential Decision Making
Marcus Pereira, David D. Fan, Gabriel Nakajima An +1
In this paper we investigate the use of MPC-inspired neural network policies for sequential decision making. We introduce an extension to the DAgger algorithm for training such pol…