Exploring Parameter Space with Structured Noise for Meta-Reinforcement Learning.
Hui XuChong ZhangJiaxing WangDeqiang OuyangYu ZhengJie ShaoPublished in: IJCAI (2020)
Keyphrases
- parameter space
- reinforcement learning
- noise model
- image space
- high dimensional
- parameter values
- noise level
- random noise
- function approximation
- starting points
- linear transformations
- multivariate data
- noisy data
- missing data
- markov decision processes
- search space
- state space
- riemannian manifolds
- likelihood function
- model free
- real world
- machine learning
- learning process
- noise reduction
- reinforcement learning algorithms
- dynamic programming
- mobile robot
- supervised learning
- learning algorithm
- transfer learning