A C++ template-based reinforcement learning library: fitting the code to the mathematics.
Hervé Frezza-BuetMatthieu GeistPublished in: J. Mach. Learn. Res. (2013)
Keyphrases
- reinforcement learning
- state space
- multi agent
- function approximation
- computer science
- optimal policy
- markov decision processes
- model fitting
- learning algorithm
- neural network
- reinforcement learning algorithms
- machine learning
- temporal difference learning
- model free
- active appearance models
- least squares
- learning process
- temporal difference
- error detection
- multi agent reinforcement learning
- code snippets