
Adaptive Federated Learning and Digital Twin for Industrial Internet of Things
Industrial Internet of Things (IoT) enables distributed intelligent serv...
read it

Learning the Linear Quadratic Regulator from Nonlinear Observations
We introduce a new problem setting for continuous control called the LQR...
read it

PCPG: Policy Cover Directed Exploration for Provable Policy Gradient Learning
Direct policy gradient methods for reinforcement learning are a successf...
read it

Information Theoretic Regret Bounds for Online Nonlinear Control
This work studies the problem of sequential control in an unknown, nonli...
read it

FLAMBE: Structural Complexity and Representation Learning of Low Rank MDPs
In order to deal with the curse of dimensionality in reinforcement learn...
read it

Provably Efficient Modelbased Policy Adaptation
The high sample complexity of reinforcement learning challenges its use ...
read it

Constrained episodic reinforcement learning in concaveconvex and knapsack settings
We propose an algorithm for tabular episodic reinforcement learning with...
read it

Arbitrary Style Transfer via MultiAdaptation Network
Arbitrary style transfer is a significant topic with both research value...
read it

Exploration in Action Space
Parameter space exploration methods with blackbox optimization have rec...
read it

Corruption Robust Exploration in Episodic Reinforcement Learning
We initiate the study of multistage episodic reinforcement learning und...
read it

Policy Poisoning in Batch Reinforcement Learning and Control
We study a security threat to batch reinforcement learning and control w...
read it

Optimal Sketching for Kronecker Product Regression and Low Rank Approximation
We study the Kronecker product regression problem, in which the design m...
read it

Imitation Learning as fDivergence Minimization
We address the problem of imitation learning with multimodal demonstrat...
read it

Provably Efficient Imitation Learning from Observation Alone
We study Imitation Learning (IL) from Observations alone (ILFO) in large...
read it

Efficient Modelfree Reinforcement Learning in Metric Spaces
Modelfree Reinforcement Learning (RL) algorithms such as Qlearning [Wa...
read it

OutcomeDriven Clustering of Acute Coronary Syndrome Patients using MultiTask Neural Network with Attention
Cluster analysis aims at separating patients into phenotypically heterog...
read it

Contrasting Exploration in Parameter and Action Space: A ZerothOrder Optimization Perspective
Blackbox optimizers that explore in parameter space have often been sho...
read it

ModelBased Reinforcement Learning in Contextual Decision Processes
We study the sample complexity of modelbased reinforcement learning in ...
read it

Contextual Memory Trees
We design and study a Contextual Memory Tree (CMT), a learning memory co...
read it

Truncated Horizon Policy Search: Combining Reinforcement Learning & Imitation Learning
In this paper, we propose to combine imitation and reinforcement learnin...
read it

Dual Policy Iteration
Recently, a novel class of Approximate Policy Iteration (API) algorithms...
read it

Recurrent Predictive State Policy Networks
We introduce Recurrent Predictive State Policy (RPSP) networks, a recurr...
read it

Sketching for Kronecker Product Regression and Psplines
TensorSketch is an oblivious linear sketch introduced in Pagh'13 and lat...
read it

PredictiveState Decoders: Encoding the Future into Recurrent Networks
Recurrent neural networks (RNNs) are a vital modeling technique that rel...
read it

RiskAware Algorithms for Adversarial Contextual Bandits
In this work we consider adversarial contextual bandits with risk constr...
read it
Wen Sun
is this you? claim profile
Member of Royal Irish Academy, Member of Academia Europaea, Foreign Member of Polish Academy of Sciences, Full Professor of Food and Biosystems Engineering at University College Dublin