| Title | Dynamic Programming: From Local Optimality to Global Optimality |
| Date | May 19, 2025 (Monday) 10:40-12:10 |
| Location | 12th floor Discussion Room |
| Abstract | In the theory of dynamic programming, an optimal policy is a policy whose lifetime value dominates that of all other policies from every possible initial condition in the state space. This raises a natural question: when does optimality from a single state imply optimality from every state? We show that, in a general setting, irreducibility of the transition kernel is sufficient for this property. Our results have important implications for modern policy-based algorithms used to solve large-scale dynamic programs in reinforcement learning and other fields. |
| Paper | Paper Link |
| Slide | |
| Note |