Sequential Learning in Artificial Intelligence - Oral Session 4

Attend a comprehensive oral session from the Uncertainty in Artificial Intelligence conference focusing on Sequential Learning. Explore four cutting-edge research papers presented over 1 hour and 33 minutes. Delve into topics including model-based robust reinforcement learning, optimistic regret bounds for online learning in adversarial Markov decision processes, group fairness in predict-then-optimize settings for restless bandits, and recursively-constrained partially observable Markov decision processes. Gain insights from researchers as they discuss their methodologies, findings, and implications for the field of artificial intelligence and machine learning. Access the full papers through the provided OpenReview links to deepen your understanding of these advanced concepts in sequential learning and decision-making under uncertainty.