Private Q-Learning with Functional Noise in Continuous Spaces.
Baoxiang WangNidhi HegdePublished in: CoRR (2019)
Keyphrases
- reinforcement learning
- cooperative
- noise level
- function approximation
- state space
- noise model
- noise free
- random noise
- privacy preserving
- signal to noise ratio
- missing data
- discrete data
- noise reduction
- multi agent
- learning algorithm
- median filter
- multiscale
- continuous state spaces
- data sets
- additive noise
- image structure
- noisy data
- optimal policy
- neural network