FPMCO decomposes multi-constraint RL into KL-projection sub-problems, achieving higher reward with lower computing than second-order rivals on the new SCIG robotics benchmark.

We investigate risk-averse stochastic optimization problems with a risk-shaping constraint in the form of a stochastic-order relation. Both univariate and multivariate orders are considered. We extend ...

Recently, a new approach for optimization of conditional value-at-risk (CVAR) was suggested and tested with several applications. For continuous distributions, CVAR is defined as the expected loss ...

The Covid-19 pandemic has triggered a wave of severe economic disruption around the world, causing widespread chaos, profound changes in the business landscape and overwhelming operational challenges.