Bayesian Multi-type Mean Field Multi-agent Imitation Learning.
Fan YangAlina VereshchakaChangyou ChenWen DongPublished in: NeurIPS (2020)
Keyphrases
- multi type
- imitation learning
- multi agent
- reinforcement learning
- bayesian inference
- relational data
- posterior distribution
- data objects
- maximum margin
- humanoid robot
- relational domains
- markov networks
- maximum likelihood
- robotic systems
- markov random field
- cost model
- bayesian networks
- em algorithm
- belief networks
- reinforcement learning methods
- posterior probability
- multiple types
- computer vision
- learning algorithm
- multi modal
- probability distribution
- first order logic
- vision system
- database systems