A Consumption and Investment Problem via a Markov Decision Processes Approach with Random Horizon.
Octavio Paredes PérezVíctor Vázquez-GuevaraHugo Cruz-SuárezPublished in: Adv. Oper. Res. (2022)
Keyphrases
- markov decision processes
- finite state
- optimal policy
- state space
- discount factor
- transition matrices
- reinforcement learning
- dynamic programming
- policy iteration
- long run
- model based reinforcement learning
- risk sensitive
- decision theoretic planning
- reachability analysis
- infinite horizon
- factored mdps
- state and action spaces
- markov decision process
- finite horizon
- action space
- reinforcement learning algorithms
- planning under uncertainty
- average reward
- average cost
- decision making
- decision processes
- machine learning
- sufficient conditions
- semi markov decision processes
- markov decision problems
- partially observable
- reward function
- decision problems
- heuristic search
- action sets
- multistage
- search space