
Ensemble and Auxiliary Tasks for DataEfficient Deep Reinforcement Learning
Ensemble and auxiliary tasks are both well known to improve the performa...
read it

Learning Latent Graph Dynamics for Deformable Object Manipulation
Manipulating deformable objects, such as cloth and ropes, is a longstan...
read it

StateAware Variational Thompson Sampling for Deep QNetworks
Thompson sampling is a wellknown approach for balancing exploration and...
read it

Factor Graph Molecule Network for Structure Elucidation
Designing a network to learn a molecule structure given its physical/che...
read it

Neuralizing Efficient Higherorder Belief Propagation
Graph neural network models have been extensively used to learn node rep...
read it

Contrastive Variational ModelBased Reinforcement Learning for Complex Observations
Deep modelbased reinforcement learning (MBRL) has achieved great sample...
read it

Effective Training Strategies for Deep Graph Neural Networks
Graph Neural Networks (GNNs) tend to suffer performance degradation as m...
read it

Multiplicative Gaussian Particle Filter
We propose a new samplingbased approach for approximate inference in fi...
read it

Discriminative Particle Filter Reinforcement Learning for Complex Partial Observations
Deep reinforcement learning is successful in decision making for sophist...
read it

Visual Relationship Detection with Low Rank NonNegative Tensor Decomposition
We address the problem of Visual Relationship Detection (VRD) which aims...
read it

An Interactive MultiTask Learning Network for EndtoEnd AspectBased Sentiment Analysis
Aspectbased sentiment analysis produces a list of aspect terms and thei...
read it

Factor Graph Neural Network
Most of the successful deep neural network architectures are structured,...
read it

Particle Filter Recurrent Neural Networks
Recurrent neural networks (RNNs) have been extraordinarily successful fo...
read it

LeTSDrive: Driving in a Crowd by Learning from Tree Search
Autonomous driving in a crowded environment, e.g., a busy traffic inters...
read it

Differentiable Algorithm Networks for Composable Robot Learning
This paper introduces the Differentiable Algorithm Network (DAN), a comp...
read it

Guided Exploration of Human Intentions for HumanRobot Interaction
Robot understanding of human intentions is essential for fluid humanrob...
read it

Adaptive Semisupervised Learning for Crossdomain Sentiment Classification
We consider the crossdomain sentiment classification problem, where a s...
read it

Integrating Algorithmic Planning and Deep Learning for Partially Observable Navigation
We propose to take a novel approach to robot system design where each bu...
read it

Exploiting Document Knowledge for Aspectlevel Sentiment Classification
Attentionbased long shortterm memory (LSTM) networks have proven to be...
read it

PORCA: Modeling and Planning for Autonomous Driving among Many Pedestrians
This paper presents a planning system for autonomous driving among many ...
read it

Autonomous Driving among Many Pedestrians: Models and Algorithms
Driving among a dense crowd of pedestrians is a major challenge for auto...
read it

Particle Filter Networks with Application to Visual Localization
Particle filtering is a powerful method for sequential state estimation ...
read it

Particle Filter Networks: EndtoEnd Probabilistic Localization From Visual Observations
Particle filters sequentially approximate posterior distributions by sam...
read it

Convolutional Sequence to Sequence Model for Human Dynamics
Human motion modeling is a classic problem in computer vision and graphi...
read it

HyPDESPOT: A Hybrid Parallel Algorithm for Online Planning under Uncertainty
Planning under uncertainty is critical for robust robot performance in u...
read it

IntentionNet: Integrating Planning and Deep Learning for GoalDirected Autonomous Navigation
How can a delivery robot navigate reliably to a destination in a new off...
read it

QMDPNet: Deep Learning for Planning under Partial Observability
This paper introduces the QMDPnet, a neural network architecture for pl...
read it

Factored Contextual Policy Search with Bayesian Optimization
Scarce data is a major challenge to scaling robot learning to truly comp...
read it

DESPOT: Online POMDP Planning with Regularization
The partially observable Markov decision process (POMDP) provides a prin...
read it

Robustness of Bayesian Poolbased Active Learning Against Prior Misspecification
We study the robustness of active learning (AL) algorithms against prior...
read it

POMDPlite for Robust Robot Planning under Uncertainty
The partially observable Markov decision process (POMDP) provides a prin...
read it

Monte Carlo Bayesian Reinforcement Learning
Bayesian reinforcement learning (BRL) encodes prior knowledge of the wor...
read it
Wee Sun Lee
is this you? claim profile