Structural Abstraction Experiments in Reinforcement Learning.
Robert FitchBernhard HengstDorian SucGreg CalbertJason B. ScholzPublished in: Australian Conference on Artificial Intelligence (2005)
Keyphrases
- reinforcement learning
- state abstraction
- temporal abstractions
- function approximation
- state space
- reinforcement learning algorithms
- structural information
- machine learning
- data sets
- decision theoretic planning
- policy search
- temporal difference learning
- robot control
- model free
- markov decision processes
- optimal policy
- learning process
- high level
- multi agent
- real time
- dynamic programming
- neural network
- artificial intelligence
- information systems
- case study
- markov decision process
- learning capabilities
- database systems
- structural features
- optimal control
- learning environment
- radial basis function
- artificial neural networks
- learning tasks
- transfer learning