AMoreBackgrounds A.1 DistributionalRL Distributional RL [2, 3, 8] is an area of RL that considers the distribution of the cumulative return Zπ(s,a) = P t=0γ
–Neural Information Processing Systems
There are two well-known techniques, called Value at Risk (VaR, or Quantile) and Conditional Value at Risk (CVaR), to manage undesirable events in the domain of finance[18].
Neural Information Processing Systems
Feb-8-2026, 01:26:24 GMT