Compound Reinforcement Learning: Theory and an Application to Finance.
Tohgoroh MatsuiTakashi GotoKiyoshi IzumiYu ChenPublished in: EWRL (2011)
Keyphrases
- reinforcement learning
- state space
- learning algorithm
- computational intelligence
- robotic control
- theoretical basis
- function approximation
- information theory
- learning process
- theoretical framework
- markov decision processes
- computational model
- optimal control
- information systems
- domain theory
- model free
- temporal difference
- machine learning