Keyphrases
- reinforcement learning
- function approximation
- recurrent neural networks
- electronic commerce
- reinforcement learning algorithms
- model free
- feed forward
- multi agent
- temporal difference
- optimal policy
- markov decision processes
- state space
- robotic control
- learning classifier systems
- optimal control
- learning algorithm
- dynamic programming
- hidden markov models
- long term
- learning process
- financial markets
- partially observable
- trading systems
- trading strategies
- temporal difference learning
- data sets