Disentangling Interaction Using Maximum Entropy Reinforcement Learning in Multi-Agent Systems.
David RotherThomas H. WeisswangeJan PetersPublished in: ECAI (2023)
Keyphrases
- maximum entropy
- learning in multi agent systems
- maximum entropy principle
- cooperative
- markov models
- reinforcement learning
- minimum cross entropy
- transformation based learning
- multi agent learning
- principle of maximum entropy
- learning agents
- iterative scaling
- class conditional
- maximum entropy model
- conditional random fields
- multi agent systems
- learning algorithm
- dynamic programming
- bayesian networks
- training data