Distributional Reinforcement Learning for Risk-Sensitive Sequential Decision Making: New T — NSF Award to University of Miami (FL,
Many critical online decision systems, including clinical support, financial risk management, and autonomous technologies, must look beyond average performance to avoid rare but catastrophic "tail events." Traditional reinforcement learning often summarizes future outcomes as a single expected value, which masks signif
| Award title | Distributional Reinforcement Learning for Risk-Sensitive Sequential Decision Making: New T |
|---|---|
| Award ID | 2610563 |
| Awardee | University of Miami |
| City | CORAL GABLES |
| State | FL |
| Amount obligated | $299,601 |
| Principal investigator | Lan Wang |
| Program | STATISTICS |
| Start date | 07/01/2026 |
| Abstract | Many critical online decision systems, including clinical support, financial risk management, and autonomous technologies, must look beyond average performance to avoid rare but catastrophic "tail events." Traditional reinforcement learning often summarizes future outcomes as a single expected value, which masks significant risks and uncertainty. This research addresses this limitation by developing distributional reinforcement learning methods that learn the full range of possible outcomes to s |
| Source | NSF Awards |
$799/mo
Try NSFGrants →