Relevance determination in reinforcement learning.
Katharina Tluk von ToschanowitzBarbara HammerHelge J. RitterPublished in: ESANN (2005)
Keyphrases
- reinforcement learning
- information retrieval
- function approximation
- temporal difference
- reinforcement learning algorithms
- state space
- test collection
- markov decision processes
- multi agent
- optimal policy
- relative importance
- partially observable
- robotic control
- radial basis function
- function approximators
- robot control
- model free
- dynamic programming
- learning algorithm