Structural Return Maximization for Reinforcement Learning.
Joshua Mason JosephJavier VélezNicholas RoyPublished in: CoRR (2014)
Keyphrases
- reinforcement learning
- function approximation
- learning algorithm
- state space
- structural information
- data sets
- multi agent
- learning process
- optimal policy
- machine learning
- robotic control
- temporal difference
- model free
- information systems
- markov decision processes
- transfer learning
- structural analysis
- stochastic approximation