Incremental State Aggregation for Value Function Estimation in Reinforcement Learning.
Takeshi MoriShin IshiiPublished in: IEEE Trans. Syst. Man Cybern. Part B (2011)
Keyphrases
- reinforcement learning
- state space
- state transitions
- transition model
- search space
- function approximation
- data aggregation
- state estimation
- estimation algorithm
- control policy
- function approximators
- aggregation operators
- accurate estimation
- model free
- data sets
- markov decision processes
- markov chain
- data driven
- learning algorithm