Cooperative Multi-agent Inverse Reinforcement Learning Based on Selfish Expert and its Behavior Archives.

Yukiko Fukumoto Masakazu Tadokoro Keiki Takadama

Published in: SSCI (2020)

Keyphrases

inverse reinforcement learning
bayesian nonparametric
cooperative multi agent
preference elicitation
partially observable environments
reward function
resource allocation
temporal difference
data mining
artificial intelligence
hidden markov models