A Q-learning Approach to a Consumption-Investment Problem
2021 ◽
Vol 10
(2)
◽
pp. 110
Keyword(s):
The paper deals with a discrete-time consumption investment problem with an infinite horizon. This problem is formulated as a Markov decision process with an expected total discounted utility as an objective function. This paper aims to presents a procedure to approximate the solution via machine learning, specifically, a Q-learning technique. The numerical results of the problem are provided.
2021 ◽
Vol 10
(2)
◽
pp. 109
2017 ◽
Vol 7
(1.5)
◽
pp. 274
2020 ◽
Vol 17
(4A)
◽
pp. 677-682
Keyword(s):
Keyword(s):
Solving infinite horizon discounted Markov decision process problems for a range of discount factors
1989 ◽
Vol 141
(2)
◽
pp. 303-317
◽
Keyword(s):
Keyword(s):
2014 ◽
Vol 46
(01)
◽
pp. 121-138
◽