Risk-averse sensor planning using distributed policy gradient.
Wann-Jiun MaDarinka DentchevaMichael M. ZavlanosPublished in: ACC (2017)
Keyphrases
- risk averse
- policy gradient
- utility function
- stochastic programming
- multi agent
- decision makers
- planning problems
- optimal control
- expected utility
- partially observable markov decision processes
- dynamic programming
- decision making
- decision theoretic
- single agent
- gradient method
- variance reduction
- portfolio management
- computational complexity