Characterizing a Brain-Based Value-Function Approximator.
Patrick C. ConnorThomas P. TrappenbergPublished in: Canadian Conference on AI (2011)
Keyphrases
- function approximators
- function approximation
- reinforcement learning
- temporal difference methods
- reinforcement learning problems
- neural network
- temporal difference
- learning tasks
- reinforcement learning algorithms
- real valued
- action space
- weight vector
- radial basis function
- decision making
- markov random field
- cost function
- decision trees
- machine learning