Towards a Self-Learning Agent: Using Ranking Functions as a Belief Representation in Reinforcement Learning.
Klaus HämingGabriele PetersPublished in: Neural Process. Lett. (2013)
Keyphrases
- learning agent
- ranking functions
- reinforcement learning
- state space
- supervised learning
- solving problems
- reinforcement learning algorithms
- learning algorithm
- web search engines
- document retrieval
- web search
- ranking algorithm
- learning tasks
- dynamic programming
- learning capabilities
- function approximation
- model free
- learning process
- markov decision processes
- information processing
- transfer learning
- optimal policy
- neural network
- knowledge based systems
- semi supervised
- search space
- multi agent
- bayesian networks
- machine learning