Integrating symmetry of environment by designing special basis functions for value function approximation in reinforcement learning.
Guo-fang WangZhou FangBo LiPing LiPublished in: ICARCV (2016)
Keyphrases
- basis functions
- reinforcement learning
- state space
- linear combination
- radial basis function
- b spline
- spherical harmonics
- wavelet bases
- matching pursuit
- markov decision processes
- lookup tables
- zernike moments
- series expansion
- dynamic programming
- learning algorithm
- temporal difference
- optimal policy
- machine learning
- function approximation
- linear program
- factored mdps
- multiscale