Multi-Agent MDP Homomorphic Networks.
Elise van der PolHerke van HoofFrans A. OliehoekMax WellingPublished in: ICLR (2022)
Keyphrases
- multi agent
- markov decision processes
- reinforcement learning
- privacy preserving
- agent based simulations
- social networks
- finite state
- utility function
- cooperative
- planning under uncertainty
- optimal policy
- markov decision process
- multiple agents
- multi agent systems
- network structure
- linear program
- network analysis
- network model
- coalition formation
- community structure
- decision theoretic
- computer networks
- heterogeneous networks
- complex networks
- probabilistic planning