Intrinsic Reward Driven Imitation Learning via Generative Model.
Xingrui YuYueming LyuIvor W. TsangPublished in: CoRR (2020)
Keyphrases
- generative model
- imitation learning
- reinforcement learning
- probabilistic model
- maximum margin
- humanoid robot
- robotic systems
- semi supervised
- bayesian framework
- prior knowledge
- em algorithm
- topic models
- posterior probability
- conditional random fields
- reward function
- model free
- state space
- reinforcement learning methods
- expectation maximization
- hidden variables
- maximum likelihood
- average reward
- machine learning
- reinforcement learning algorithms
- similarity measure