News

  • 10/2022: "Optimal Multi-armed Bandits Policies with Light-tailed Risk", Informs Annual Meeting 2022
  • 10/2022: "Online Matching with Reusable Network Resources and Decaying Rewards",┬áInforms Annual Meeting 2022
  • 05/2022: First TA completed! Class: 6.231 Dynamic Programming and Reinforcement Learning