Multi-agent Adversarial Inverse Reinforcement Learning with Latent Variables.
Nate GruverJiaming SongMykel J. KochenderferStefano ErmonPublished in: AAMAS (2020)
Keyphrases
- latent variables
- multi agent
- inverse reinforcement learning
- probabilistic model
- preference elicitation
- posterior distribution
- random variables
- prior knowledge
- topic models
- reward function
- gaussian process
- reinforcement learning
- variational bayes
- real valued
- multiple agents
- approximate inference
- temporal difference
- hidden variables
- exact inference
- observed variables
- factor graphs
- probabilistic graphical models
- gaussian processes
- generative model
- bayesian networks