Safe Policy Search Using Gaussian Process Models.
Kyriakos PolymenakosAlessandro AbateStephen J. RobertsPublished in: AAMAS (2019)
Keyphrases
- policy search
- gaussian process models
- gaussian processes
- gaussian process
- reinforcement learning
- continuous state
- human pose estimation
- reinforcement learning algorithms
- dynamic programming
- reward function
- regression model
- policy gradient
- markov decision processes
- partially observable markov decision processes
- feature selection
- markov decision problems
- multi agent
- learning algorithm
- latent variables
- transfer learning
- semi supervised
- state space