Dynamic Regret in Online Convex Optimization with Indicator Switching Costs
Dynamic regret with fixed switching penalties, via a meta-learning framework that is minimax-optimal for piecewise-constant comparators.
On the Dynamic Regret of Following the Regularized Leader: Optimism with History Pruning
Dynamic-regret analysis of FTRL with optimistic predictions and a history-pruning technique that improves bounds.
Multi-Target Path Planning with Probabilistic Detection in Cluttered Environments
Multi-target path planning with probabilistic detection in cluttered environments.
noor-khial
An Online Learning Framework for UAV Target Search Missions in Non-stationary Environments
Online learning for UAV target search missions in non-stationary environments.
noor-khial
Adaptive Online Non-stochastic Control
Adaptive-regret online non-stochastic control algorithms with strong guarantees in changing environments.
Federated Learning for Online Resource Allocation in Mobile Edge Computing: A Deep Reinforcement Learning Approach
Federated learning + deep RL for online resource allocation in mobile edge computing.
jingjing-zheng
Optimistic No-regret Algorithms for Discrete Caching
No-regret algorithms for discrete caching that integrate untrusted predictions for improved performance.
Online Caching with Optimistic Learning
Online caching with optimistic learning, exploiting predictions while keeping no-regret guarantees.
Rational Contracts: Data-Driven Service Provisioning in Blockchain-Powered Systems
Rational contracts for data-driven service provisioning in blockchain-powered systems.
Real-Time Scheduling for Electric Vehicles Charging/Discharging Using Reinforcement Learning
Reinforcement learning for real-time EV charging/discharging scheduling.