Integration of imitation learning using GAIL and reinforcement learning using task-achievement rewards via probabilistic graphical model.
Akira KinoseTadahiro TaniguchiPublished in: Adv. Robotics (2020)
Keyphrases
- reinforcement learning
- imitation learning
- probabilistic graphical models
- graphical models
- reinforcement learning methods
- markov decision processes
- model free
- state space
- optimal policy
- reinforcement learning algorithms
- learning algorithm
- first order logic
- approximate inference
- machine learning
- belief propagation
- latent variables
- markov networks
- probabilistic inference
- exact inference
- supervised learning
- transfer learning
- conditional random fields
- random variables
- text classification
- hidden variables
- belief functions
- parameter learning
- cross validation
- active learning