Search Results for author:
Found 20 papers, 10 papers with code
A Non-Monolithic Policy Approach of Offline-to-Online Reinforcement Learning
An existing approach, Policy Expansion (PEX), utilizes a policy set composed of both policies without modifying the offline policy for exploration and learning.
Functional Stochastic Gradient MCMC for Bayesian Neural Networks
Classical parameter-space Bayesian inference for Bayesian neural networks (BNNs) suffers from several unresolved prior issues, such as knowledge encoding intractability and pathological behaviours in deep networks, which can lead to improper posterior inference.
LSTM Autoencoder-based Deep Neural Networks for Barley Genotype-to-Phenotype Prediction
Artificial Intelligence (AI) has emerged as a key driver of precision agriculture, facilitating enhanced crop productivity, optimized resource use, farm sustainability, and informed decision-making.
A Behavior-Aware Approach for Deep Reinforcement Learning in Non-stationary Environments without Known Change Points
The model adapts to the new environment through behavior regularization based on the extent of changes.
Decoupling Exploration and Exploitation for Unsupervised Pre-training with Successor Features
Our suggested model is termed Non-Monolithic unsupervised Pre-training with Successor features (NMPS), which improves the performance of the original monolithic exploration method of pre-training with SFs.
Group-Aware Coordination Graph for Multi-Agent Reinforcement Learning
To overcome these limitations, we present a novel approach to infer the Group-Aware Coordination Graph (GACG), which is designed to capture both the cooperation between agent pairs based on current observations and group-level dependencies from behaviour patterns observed across trajectories.
Inferring Latent Temporal Sparse Coordination Graph for Multi-Agent Reinforcement Learning
The LTS-CG leverages agents' historical observations to calculate an agent-pair probability matrix, where a sparse graph is sampled from and used for knowledge exchange between agents, thereby simultaneously capturing agent dependencies and relation uncertainty.
Layer-diverse Negative Sampling for Graph Neural Networks
Experiments on various real-world graph datasets demonstrate the effectiveness of our approach in improving the diversity of negative samples and overall learning performance.
An Autonomous Non-monolithic Agent with Multi-mode Exploration based on Options Framework
The issue of `when' of a monolithic exploration in the usual RL exploration behaviour binds an exploratory action to an exploitational action of an agent.
Graph Convolutional Neural Networks with Diverse Negative Samples via Decomposed Determinant Point Processes
However, there are more non-neighbour nodes in the whole graph, which provide diverse and useful information for the representation update.
Learning from the Dark: Boosting Graph Convolutional Neural Networks with Diverse Negative Samples
An interesting way to understand GCNs is to think of them as a message passing mechanism where each node updates its representation by accepting information from its neighbours (also known as positive samples).
Bayesian Transfer Learning: An Overview of Probabilistic Graphical Models for Transfer Learning
Transfer learning where the behavior of extracting transferable knowledge from the source domain(s) and reusing this knowledge to target domain has become a research area of great interest in the field of artificial intelligence.
Deep Bayesian Estimation for Dynamic Treatment Regimes with a Long Follow-up Time
Causal effect estimation for dynamic treatment regimes (DTRs) contributes to sequential decision making.
Hierarchical Reinforcement Learning with Optimal Level Synchronization based on a Deep Generative Model
We propose a novel HRL model supporting the optimal level synchronization using the off-policy correction technique with a deep generative model.
Hierarchical Reinforcement Learning
reinforcement-learning
+1
Path Integral Based Convolution and Pooling for Graph Neural Networks
Borrowing ideas from physics, we propose a path integral based graph neural networks (PAN) for classification and regression tasks on graphs.
Open Set Domain Adaptation: Theoretical Bound and Algorithm
The aim of unsupervised domain adaptation is to leverage the knowledge in a labeled (source) domain to improve a model's learning performance with an unlabeled (target) domain -- the basic strategy being to mitigate the effects of discrepancies between the two distributions.
Ranked #24 on
Domain Adaptation
on Office-Home
Cooperative Hierarchical Dirichlet Processes: Superposition vs. Maximization
The cooperative hierarchical structure is a common and significant data structure observed in, or adopted by, many research areas, such as: text mining (author-paper-word) and multi-label classification (label-instance-feature).
Dependent Indian Buffet Process-based Sparse Nonparametric Nonnegative Matrix Factorization
Under this same framework, two classes of correlation function are proposed (1) using Bivariate beta distribution and (2) using Copula function.
Infinite Author Topic Model based on Mixed Gamma-Negative Binomial Process
One branch of these works is the so-called Author Topic Model (ATM), which incorporates the authors's interests as side information into the classical topic model.
Nonparametric Relational Topic Models through Dependent Gamma Processes
Traditional Relational Topic Models provide a way to discover the hidden topics from a document network.
