no code implementations • 6 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).
no code implementations • 12 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.
no code implementations • 4 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.
no code implementations • 4 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.
no code implementations • 28 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.
no code implementations • 8 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.
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.
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.
no code implementations • 25 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.
no code implementations • 25 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.
1 code implementation • 3 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
no code implementations • 15 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.
no code implementations • 21 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
no code implementations • ICML 2017 • Yichen Wang, Grady Williams, Evangelos Theodorou, Le Song
Temporal point processes have been widely applied to model event sequence data generated by online users.
no code implementations • 22 Aug 2016 • Yunpeng Pan, Xinyan Yan, Evangelos Theodorou, Byron Boots
Robotic systems must be able to quickly and robustly make decisions when operating in uncertain and dynamic environments.
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.
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).