Risk-Averse Trust Region Optimization for Reward-Volatility Reduction.
Lorenzo BisiLuca SabbioniEdoardo VittoriMatteo PapiniMarcello RestelliPublished in: IJCAI (2020)
Keyphrases
- trust region
- risk averse
- optimization methods
- stochastic programming
- line search
- global optimum
- optimization method
- optimization algorithm
- decision makers
- utility function
- reinforcement learning
- optimization problems
- column generation
- hessian matrix
- simulated annealing
- stock price
- linear program
- multistage
- quadratic programming
- robust optimization
- multiple objectives
- portfolio management
- dynamic programming
- lower bound