Skip to content
NeurIPS 2026 planner

Tutorial · Sydney

From Heuristics to Guarantees: Bandit and RL Blueprint for Reliable Agentic-AI

When
Mon 7 Dec 2026, 14:00–17:00 AEDT
Where
Grand Ballroom B2 & B3, ICC Sydney
Convention Centre, Level 5
Authors
Aadirupa Saha, Arun Verma, Djallel Bouneffouf
Organisations
University of Illinios, Singapore-MIT Alliance for Research and Technology Centre, IBM
QRS classification
Reinforcement learning, Learning theory

Open in scheduleOfficial page