Barrier Functions for Multiagent-POMDPs with DTL Specifications.
Mohamadreza AhmadiAndrew SingletaryJoel W. BurdickAaron D. AmesPublished in: CDC (2020)
Keyphrases
- multi agent
- distributed constraint optimization
- markov decision processes
- planning under uncertainty
- single agent
- reinforcement learning
- dynamic programming
- multi agent systems
- cooperative
- intelligent agents
- multiagent systems
- optimal policy
- multiple agents
- belief state
- functional requirements
- delay insensitive
- partially observable markov decision