
Expert Selection in HighDimensional Markov Decision Processes
In this work we present a multiarmed bandit framework for online expert...
read it

Improving InputOutput Linearizing Controllers for Bipedal Robots via Reinforcement Learning
The main drawbacks of inputoutput linearizing controllers are the need ...
read it

Technical Report: Adaptive Control for Linearizable Systems Using OnPolicy Reinforcement Learning
This paper proposes a framework for adaptively learning a feedback linea...
read it

Exponentially Stable First Order Control on Matrix Lie Groups
We present a novel first order controller for systems evolving on matrix...
read it

LESS is More: Rethinking Probabilistic Models of Human Behavior
Robots need models of human behavior for both inferring human goals and ...
read it

Persistency of Excitation for Robustness of Neural Networks
When an online learning algorithm is used to estimate the unknown parame...
read it

Feedback Linearization for Unknown Systems via Reinforcement Learning
We present a novel approach to control design for nonlinear systems, whi...
read it

Maximum Likelihood Constraint Inference for Inverse Reinforcement Learning
While most approaches to the problem of Inverse Reinforcement Learning (...
read it

PolicyGradient Algorithms Have No Guarantees of Convergence in Continuous Action and State MultiAgent Settings
We show by counterexample that policygradient algorithms have no guaran...
read it

Competitive Statistical Estimation with Strategic Data Sources
In recent years, data has played an increasingly important role in the e...
read it

CrossEntropy Loss and LowRank Features Have Responsibility for Adversarial Examples
Stateoftheart neural networks are vulnerable to adversarial examples;...
read it

On Finding Local Nash Equilibria (and Only Local Nash Equilibria) in ZeroSum Games
We propose a twotimescale algorithm for finding local Nash equilibria i...
read it

Hierarchical GameTheoretic Planning for Autonomous Vehicles
The actions of an autonomous vehicle on the road affect and are affected...
read it

Step Size Matters in Deep Learning
Training a neural network with the gradient descent algorithm gives rise...
read it

Modeling Supervisor Safe Sets for Improving Collaboration in HumanRobot Teams
When a human supervisor collaborates with a team of robots, their attent...
read it

Generating Plans that Predict Themselves
Collaboration requires coordination, and we coordinate by anticipating o...
read it

Goal Inference Improves Objective and Perceived Performance in HumanRobot Collaboration
The study of humanrobot interaction is fundamental to the design and us...
read it

People as Sensors: Imputing Maps from Human Actions
Despite growing attention in autonomy, there are still many open problem...
read it

PragmaticPedagogic Value Alignment
For an autonomous system to provide value (e.g., to customers, designers...
read it

Towards Verified Artificial Intelligence
Verified artificial intelligence (AI) is the goal of designing AIbased ...
read it

Dissimilaritybased Sparse Subset Selection
Finding an informative subset of a large collection of data points or mo...
read it

Sparse Illumination Learning and Transfer for SingleSample Face Recognition with Image Corruption and Misalignment
Singlesample face recognition is one of the most challenging problems i...
read it

Robust Subspace System Identification via Weighted Nuclear Norm Optimization
Subspace identification is a classical and very well studied problem in ...
read it

Compressive Shift Retrieval
The classical shift retrieval problem considers two signals in vector fo...
read it

Quadratic Basis Pursuit
In many compressive sensing problems today, the relationship between the...
read it

On the Lagrangian Biduality of Sparsity Minimization Problems
Recent results in Compressive Sensing have shown that, under certain con...
read it

Fast L1Minimization Algorithms For Robust Face Recognition
L1minimization refers to finding the minimum L1norm solution to an und...
read it
S. Shankar Sastry
is this you? claim profile
Dean and Roy W. Carlson Professor of Engineering at University of California, Berkeley