Sign in
Modeling POMDPs for generating and simulating stock investment policies.
Augusto Cesar Espíndola Baffa
Angelo E. M. Ciarlini
Published in:
SAC (2010)
Keyphrases
</>
partially observable markov decision processes
stock market
reinforcement learning
optimal policy
decision making
markov decision problems
policy gradient methods
search algorithm
state space
sufficient conditions
long run