Reinforcement Learning from a Mixture of Interpretable Experts.
Riad AkrourDavide TateoJan PetersPublished in: CoRR (2020)
Keyphrases
- reinforcement learning
- function approximation
- mixture model
- state space
- temporal difference
- reinforcement learning algorithms
- multi agent
- learning process
- machine learning
- expectation maximization
- optimal policy
- learning algorithm
- model free
- robotic control
- transition model
- autonomous learning
- fitted q iteration
- gaussian distribution
- human experts
- transfer learning
- domain experts
- partially observable
- gaussian model
- robot control
- markov decision process
- expert finding
- reinforcement learning methods
- policy gradient
- domain specific