Maximum Causal Entropy Inverse Reinforcement Learning for Mean-Field Games.
Berkay AnahtarciCan Deha KariksizNaci SaldiPublished in: CoRR (2024)
Keyphrases
- inverse reinforcement learning
- bayesian nonparametric
- partially observable environments
- preference elicitation
- reward function
- markov random field
- closed form
- markov networks
- belief networks
- nash equilibria
- variational inference
- game theory
- cooperative games
- bayesian networks
- gaussian process
- temporal difference
- em algorithm
- multi criteria
- decision making
- bayesian inference