
Iterative Amortized Policy Optimization
Policy networks are a central feature of deep reinforcement learning (RL...
read it

Distributionally Robust Learning for Unsupervised Domain Adaptation
We propose a distributionally robust learning (DRL) method for unsupervi...
read it

Learning Differentiable Programs with Admissible Neural Heuristics
We study the problem of learning differentiable functions expressed as p...
read it

Active Learning under Label Shift
Distribution shift poses a challenge for active data collection in the r...
read it

Graph Neural Networks for the Prediction of SubstrateSpecific Organic Reaction Conditions
We present a systematic investigation using graph neural networks (GNNs)...
read it

Deep Bayesian Quadrature Policy Optimization
We study the problem of obtaining accurate policy gradient estimates. Th...
read it

Averagecase Complexity of Teaching Convex Polytopes via Halfspace Queries
We examine the task of locating a target region among those induced by i...
read it

Learning compositional functions via multiplicative weight updates
Compositionality is a basic structural feature of both biological and ar...
read it

Competitive Policy Optimization
A core challenge in policy optimization in competitive Markov decision p...
read it

ChanceConstrained Trajectory Optimization for Safe Exploration and Learning of Nonlinear Systems
Learningbased control algorithms require collection of abundant supervi...
read it

A General Large Neighborhood Search Framework for Solving Integer Programs
This paper studies how to design abstractions of largescale combinatori...
read it

Human PreferenceBased Learning for Highdimensional Optimization of Exoskeleton Walking Gaits
Understanding users' gait preferences of a lowerbody exoskeleton requir...
read it

NeuralSwarm: Decentralized CloseProximity Multirotor Control Using Learned Interactions
In this paper, we present NeuralSwarm, a nonlinear decentralized stable...
read it

GLAS: GlobaltoLocal Safe Autonomy Synthesis for MultiRobot Motion Planning with EndtoEnd Learning
We present GLAS: GlobaltoLocal Autonomy Synthesis, a provablysafe, au...
read it

Multiresolution Tensor Learning for Efficient and Interpretable Spatial Analysis
Efficient and interpretable spatial analysis is crucial in many fields s...
read it

Beyond NoRegret: Competitive Control via Online Optimization with Memory
This paper studies online control with adversarial disturbances using to...
read it

On the distance between two neural networks and the stability of learning
How far apart are two neural networks? This is a foundational question i...
read it

Learning for SafetyCritical Control with Control Barrier Functions
Modern nonlinear control theory seeks to endow systems with properties o...
read it

Empirical Study of OffPolicy Policy Evaluation for Reinforcement Learning
Offpolicy policy evaluation (OPE) is the problem of estimating the onli...
read it

Triply Robust OffPolicy Evaluation
We propose a robust regression approach to offpolicy evaluation (OPE) f...
read it

Landmark Ordinal Embedding
In this paper, we aim to learn a lowdimensional Euclidean representatio...
read it

Learning Calibratable Policies using Programmatic StyleConsistency
We study the important and challenging problem of controllable generatio...
read it

PreferenceBased Learning for Exoskeleton Gait Optimization
This paper presents a personalized gait optimization framework for lower...
read it

Dueling Posterior Sampling for PreferenceBased Reinforcement Learning
In preferencebased reinforcement learning (RL), an agent interacts with...
read it

An EncoderDecoder Based Approach for Anomaly Detection with Application in Additive Manufacturing
We present a novel unsupervised deep learning approach that utilizes the...
read it

ImitationProjected Policy Gradient for Programmatic Reinforcement Learning
We present ImitationProjected Policy Gradient (IPPG), an algorithmic fr...
read it

ImitationProjected Programmatic Reinforcement Learning
We study the problem of programmatic reinforcement learning, in which po...
read it

Cotraining for Policy Learning
We study the problem of learning sequential decisionmaking policies in ...
read it

Robust Regression for Safe Exploration in Control
We study the problem of safe learning and exploration in sequential cont...
read it

Control Regularization for Reduced Variance Reinforcement Learning
Dealing with high variance is a significant challenge in modelfree rein...
read it

Batched Stochastic Bayesian Optimization via Combinatorial Constraints Design
In many highthroughput experimental design settings, such as those comm...
read it

Batch Policy Learning under Constraints
When learning policies for realworld domains, two important questions a...
read it

A Control Lyapunov Perspective on Episodic Learning via Projection to State Stability
The goal of this paper is to understand the impact of learning on contro...
read it

Episodic Learning with Control Lyapunov Functions for Uncertain Robotic Systems
Many modern nonlinear control methods aim to endow systems with guarante...
read it

NAOMI: NonAutoregressive Multiresolution Sequence Imputation
Missing value imputation is a fundamental problem in modeling spatiotemp...
read it

Neural Lander: Stable Drone Landing Control using Learned Dynamics
Precise trajectory control near ground is difficult for multirotor dron...
read it

Optimizing Photonic Nanostructures via Multifidelity Gaussian Processes
We apply numerical methods in combination with finitedifferencetimedo...
read it

A General Method for Amortizing Variational Filtering
We introduce the variational filtering EM algorithm, a simple, generalp...
read it

A General Framework for Multifidelity Bayesian Optimization with Gaussian Processes
How can we efficiently gather information to optimize an unknown functio...
read it

PhaseLink: A Deep Learning Approach to Seismic Phase Association
Seismic phase association is a fundamental task in seismology that perta...
read it

Iterative Amortized Inference
Inference models are a key component in scaling variational inference to...
read it

Stagewise Safe Bayesian Optimization with Gaussian Processes
Enforcing safety is a key aspect of many problems pertaining to sequenti...
read it

Teaching Multiple Concepts to Forgetful Learners
How can we help a forgetful learner learn multiple concepts within a lim...
read it

Learning to Search via SelfImitation
We study the problem of learning a good search policy. To do so, we prop...
read it

Generative MultiAgent Behavioral Cloning
We propose and study the problem of generative multiagent behavioral cl...
read it

Detecting Adversarial Examples via Neural Fingerprinting
Deep neural networks are vulnerable to adversarial examples, which drama...
read it

Hierarchical Imitation and Reinforcement Learning
We study the problem of learning policies over long time horizons. We pr...
read it

Teaching Categories to Human Learners with Visual Explanations
We study the problem of computerassisted teaching with explanations. Co...
read it

Multiresolution Tensor Learning for LargeScale Spatial Data
Highdimensional tensor models are notoriously computationally expensive...
read it

Understanding the Role of Adaptivity in Machine Teaching: The Case of Version Space Learners
In realworld applications of education and human teaching, an effective...
read it
Yisong Yue
verfied profile
Assistant professor in the Computing and Mathematical Sciences Department at the California Institute of Technology. Previously a research scientist at Disney Research. He received a Ph.D. from Cornell University and a B.S. from the University of Illinois at UrbanaChampaign.