Variance-Penalized Reinforcement Learning for Risk-Averse Asset Allocation.
Makoto SatoShigenobu KobayashiPublished in: IDEAL (2000)
Keyphrases
- portfolio management
- risk averse
- asset allocation
- reinforcement learning
- portfolio selection
- portfolio optimization
- transaction costs
- financial data
- state space
- markov decision processes
- optimal policy
- optimal control
- factor analysis
- decision making
- dynamic programming
- markov chain
- theoretical framework
- optimal solution