A simple mixture policy parameterization for improving sample efficiency of CVaR optimization
Reinforcement learning algorithms utilizing policy gradients (PG) to optimize Conditional Value at Risk (CVaR) face significant challenges with sample inefficiency, hindering their practical applications. This inefficiency stems from two main facts: a focus on tail-end performance that overlooks man...
| Үндсэн зохиолчид: | , , , , |
|---|---|
| Формат: | Conference item |
| Хэл сонгох: | English |
| Хэвлэсэн: |
University of Massachusetts Amherst
2024
|