Multi-agent reinforcement learning algorithm to solve a partially-observable multi-agent problem in disaster response.
Hyun-Rok LeeTaesik LeePublished in: Eur. J. Oper. Res. (2021)
Keyphrases
- multi agent
- partially observable
- reinforcement learning
- disaster response
- state space
- partial observability
- markov decision processes
- dynamical systems
- decision problems
- multiple agents
- graphical models
- belief state
- partially observable environments
- real time
- partially observable markov decision processes
- single agent
- dynamic programming
- expert systems
- knowledge base