Heterogeneous Stochastic Interactions for Multiple Agents in a Multi-armed Bandit Problem.

Udari Madhushani Naomi Ehrich Leonard

Published in: CoRR (2019)

Keyphrases

multiple agents
multi agent
single agent
monte carlo
multi agent coordination
neural network
agent societies
learning algorithm
multi agent systems
multi criteria
reward function
preference relations
multi armed bandit
stochastic programming
interaction patterns
stochastic optimization
learning automata
real world