Mean-Semivariance Policy Optimization via Risk-Averse Reinforcement Learning.
Xiaoteng MaShuai MaLi XiaQianchuan ZhaoPublished in: J. Artif. Intell. Res. (2022)
Keyphrases
- risk averse
- reinforcement learning
- stochastic programming
- optimal policy
- risk neutral
- multistage
- risk aversion
- decision makers
- utility function
- markov decision processes
- control policy
- optimization algorithm
- dynamic programming
- inventory level
- optimization problems
- portfolio management
- state space
- markov decision process
- action space
- markov decision problems
- optimization method
- optimization methods
- policy iteration
- function approximators
- combinatorial optimization
- partially observable
- long run
- genetic algorithm
- decision problems
- linear program
- decision making
- learning algorithm