A Reinforcement Learning Approach for Solving the Mean Variance Customer Portfolio in Partially Observable Models.
Erick AsiainJulio B. ClempnerAlexander S. PoznyakPublished in: Int. J. Artif. Intell. Tools (2018)
Keyphrases
- partially observable
- reinforcement learning
- markov decision problems
- markov decision processes
- state space
- hidden state
- partially observable environments
- partial observability
- portfolio optimization
- dynamical systems
- probabilistic model
- decision making
- partially observable domains
- portfolio selection
- decision problems
- hidden variables
- belief state
- long run
- action models
- infinite horizon
- data mining
- optimal policy
- knowledge base
- learning algorithm