Bounding the Probability of Resource Constraint Violations in Multi-Agent MDPs.
Frits de NijsErwin WalravenMathijs Michiel de WeerdtMatthijs T. J. SpaanPublished in: AAAI (2017)
Keyphrases
- constraint violations
- multi agent
- reinforcement learning
- markov decision processes
- hard constraints
- temporal constraints
- planning under uncertainty
- state space
- upper bound
- single agent
- multi agent systems
- multiple criteria
- soft constraints
- probability distribution
- optimal policy
- neural network
- multiple agents
- image segmentation