Concurrent Learning of Control in Multi-agent Sequential Decision Tasks
Computing Sciences and Computer Engineering
The overall objective of this project was to develop multi-agent reinforcement learning (MARL) approaches for intelligent agents to autonomously learn distributed control policies in decentralized partially observable Markov decision processes (Dec-POMDPs), without prior knowledge of the model parameters.
(2018). Concurrent Learning of Control in Multi-agent Sequential Decision Tasks. .
Available at: https://aquila.usm.edu/fac_pubs/17151