Effects of Hyper-Parameters for Deep Reinforcement Learning in Robotic Motion Mimicry: A Preliminary Study.
Taewoo KimJoo-Haeng LeePublished in: UR (2019)
Keyphrases
- hyperparameters
- reinforcement learning
- model selection
- cross validation
- bayesian framework
- closed form
- support vector
- random sampling
- bayesian inference
- em algorithm
- gaussian process
- noise level
- prior information
- sample size
- image sequences
- maximum likelihood
- motion estimation
- posterior distribution
- real robot
- incremental learning
- variational bayes
- missing values
- maximum a posteriori
- learning algorithm
- bayesian methods
- incomplete data
- machine learning
- natural images
- state space
- data sets