Search Results for author:
Found 17 papers, 5 papers with code
Follow-the-Perturbed-Leader with Fréchet-type Tail Distributions: Optimality in Adversarial Bandits and Best-of-Both-Worlds
In this paper, we establish a sufficient condition for perturbations to achieve $\mathcal{O}(\sqrt{KT})$ regrets in the adversarial setting, which covers, e. g., Fr\'{e}chet, Pareto, and Student-$t$ distributions.
Learning Uncertainty-Aware Temporally-Extended Actions
In reinforcement learning, temporal abstraction in the action space, exemplified by action repetition, is a technique to facilitate policy learning through extended actions.
Doubly Perturbed Task Free Continual Learning
Specifically, for input perturbation, we propose an approximate perturbation method that injects noise into the input data as well as the feature vector and then interpolates the two perturbed samples.
Model-based Offline Reinforcement Learning with Count-based Conservatism
In this paper, we propose a model-based offline reinforcement learning method that integrates count-based conservatism, named $\texttt{Count-MORL}$.
Combinatorial Neural Bandits
Approximating this unknown score function with deep neural networks, we propose algorithms: Combinatorial Neural UCB ($\texttt{CN-UCB}$) and Combinatorial Neural Thompson Sampling ($\texttt{CN-TS}$).
Model-Based Reinforcement Learning with Multinomial Logistic Function Approximation
In this paper, we establish a provably efficient RL algorithm for the MDP whose state transition is given by a multinomial logistic model.
Model-based Reinforcement Learning
reinforcement-learning
+1
Squeeze All: Novel Estimator and Self-Normalized Bound for Linear Contextual Bandits
We propose a linear contextual bandit algorithm with $O(\sqrt{dT\log T})$ regret bound, where $d$ is the dimension of contexts and $T$ isthe time horizon.
Personalized Federated Learning with Server-Side Information
Personalized Federated Learning (FL) is an emerging research field in FL that learns an easily adaptable global model in the presence of data heterogeneity among clients.
Multinomial Logit Contextual Bandits: Provable Optimality and Practicality
We propose upper confidence bound based algorithms for this MNL contextual bandit.
Sparsity-Agnostic Lasso Bandit
We consider a stochastic contextual bandit problem where the dimension $d$ of the feature vectors is potentially large, however, only a sparse subset of features of cardinality $s_0 \ll d$ affect the reward function.
Sequential Anomaly Detection using Inverse Reinforcement Learning
In order to construct a reliable anomaly detection method and take into consideration the confidence of the predicted anomaly score, we adopt a Bayesian approach for IRL.
Thompson Sampling for Multinomial Logit Contextual Bandits
The feedback here is the item that the user picks from the assortment.
Counting and Segmenting Sorghum Heads
We also propose a novel instance segmentation algorithm using the estimated density map, to identify the individual panicles in the presence of occlusion.
Crowd Counting with Decomposed Uncertainty
Uncertainty quantification accompanied by point estimation can lead to a more informed decision, and even improve the prediction quality.
Adaptive Pattern Matching with Reinforcement Learning for Dynamic Graphs
We propose an incremental graph pattern matching algorithm to deal with time-evolving graph data and also propose an adaptive optimization system based on reinforcement learning to recompute vertices in the incremental process more efficiently.
Databases
Directed Exploration in PAC Model-Free Reinforcement Learning
We study an exploration method for model-free RL that generalizes the counter-based exploration bonus methods and takes into account long term exploratory value of actions rather than a single step look-ahead.
Graph Topological Features via GAN
Inspired by the success of generative adversarial networks (GANs) in image domains, we introduce a novel hierarchical architecture for learning characteristic topological features from a single arbitrary input graph via GANs.
