Reinforcement Learning on a Futures Market Simulator.
Koichi MoriyamaMitsuhiro MatsumotoKen-ichi FukuiSatoshi KuriharaMasayuki NumaoPublished in: J. Univers. Comput. Sci. (2008)
Keyphrases
- reinforcement learning
- futures market
- short run
- real robot
- function approximation
- state space
- reinforcement learning algorithms
- temporal difference
- learning algorithm
- optimal policy
- markov decision processes
- machine learning
- long run
- simulation model
- optimal control
- model free
- multi agent
- learning process
- action selection
- search algorithm