Simultaneous policy learning and latent state inference for imitating driver behavior.
Jeremy MortonMykel J. KochenderferPublished in: ITSC (2017)
Keyphrases
- learning algorithm
- reinforcement learning
- boltzmann machine
- active learning
- knowledge acquisition
- probabilistic inference
- inference process
- hidden variables
- state space
- optimal policy
- learning tasks
- learning problems
- prior knowledge
- inductive inference
- action selection
- parameter learning
- markov decision process
- probability distribution
- markov logic
- learning process