Login / Signup
Dynamic Safe Interruptibility for Decentralized Multi-Agent Reinforcement Learning.
El Mahdi El Mhamdi
Rachid Guerraoui
Hadrien Hendrikx
Alexandre Maurer
Published in:
NIPS (2017)
Keyphrases
</>
multi agent reinforcement learning
multi agent
dynamic environments
cooperative
neural network
reinforcement learning
expert systems
domain knowledge
markov chain
sufficient conditions
autonomous agents
fuzzy neural network
stochastic games
multi agent learning