Mean-Semivariance Policy Optimization via Risk-Averse Reinforcement Learning.
Xiaoteng MaShuai MaLi XiaQianchuan ZhaoPublished in: CoRR (2022)
Keyphrases
- risk averse
- reinforcement learning
- stochastic programming
- risk neutral
- optimal policy
- multistage
- utility function
- decision makers
- function approximation
- markov decision process
- risk aversion
- linear program
- optimization algorithm
- optimization method
- learning algorithm
- portfolio management
- function approximators
- partially observable
- optimization methods
- control policy
- state space
- markov decision processes
- control policies
- optimization problems
- average cost
- multiple objectives
- policy iteration
- action space
- probability distribution
- markov chain