Non-symmetric Preferences in the IPA Market with Reinforcement Learning.
Eduardo Rodrigues GomesRyszard KowalczykPublished in: IAT (2008)
Keyphrases
- reinforcement learning
- decision making
- function approximation
- learning process
- user preferences
- reinforcement learning algorithms
- model free
- markov decision processes
- preference elicitation
- multi agent reinforcement learning
- policy search
- optimal policy
- state space
- foreign exchange
- robotic control
- neural network
- market share
- qualitative preferences
- trading strategies
- action space
- temporal difference
- learning problems
- dynamic programming
- machine learning