Integration of Imitation Learning using GAIL and Reinforcement Learning using Task-achievement Rewards via Probabilistic Generative Model.
Akira KinoseTadahiro TaniguchiPublished in: CoRR (2019)
Keyphrases
- generative model
- reinforcement learning
- imitation learning
- probabilistic model
- function approximation
- markov decision processes
- bayesian framework
- reinforcement learning methods
- posterior probability
- reinforcement learning algorithms
- prior knowledge
- model free
- state space
- semi supervised
- conditional random fields
- em algorithm
- machine learning
- reward function
- optimal policy
- dynamic programming
- temporal difference
- learning algorithm
- learning problems
- data sets
- supervised learning
- hidden variables
- learning process
- transfer learning
- topic models
- action space
- hidden state