Basis Adaptation for Sparse Nonlinear Reinforcement Learning.
Sridhar MahadevanStephen GiguereNicholas JacekPublished in: AAAI (2013)
Keyphrases
- reinforcement learning
- sparse linear
- high dimensional
- multi agent
- sparse data
- high dimension
- linear transform
- state space
- optimal policy
- machine learning
- adaptation process
- function approximation
- multi agent reinforcement learning
- nonlinear equations
- markov decision process
- learning process
- artificial neural networks
- e learning