IVDR: Imitation learning with Variational inference and Distributional Reinforcement learning to find Optimal Driving Strategy.
Kihyung JooSimon S. WooPublished in: ICMLA (2021)
Keyphrases
- imitation learning
- reinforcement learning
- variational inference
- bayesian inference
- closed form
- dynamic programming
- state space
- probabilistic model
- posterior distribution
- maximum margin
- reinforcement learning methods
- robotic systems
- machine learning
- latent dirichlet allocation
- humanoid robot
- markov decision processes
- mixture model
- probabilistic graphical models
- co occurrence
- reinforcement learning algorithms
- probabilistic inference
- variational methods
- temporal difference
- model free
- gaussian process
- optimal policy
- learning algorithm