2 papers
cs.LG2025
Smoothed Online Optimization for Target Tracking: Robust and Learning-Augmented Algorithms
Ali Zeynali, Mahsa Sahebdel, Qingsong Liu +2
We introduce the Smoothed Online Optimization for Target Tracking (SOOTT) problem, a new framework that integrates three key objectives in online decision-making under uncertainty:…
cs.AI2024
A Safe Exploration Strategy for Model-free Task Adaptation in Safety-constrained Grid Environments
Erfan Entezami, Mahsa Sahebdel, Dhawal Gupta
Training a model-free reinforcement learning agent requires allowing the agent to sufficiently explore the environment to search for an optimal policy. In safety-constrained enviro…