Exploiting structure in decentralized Markov decision processes
While formal, decision-theoretic models such as the Markov Decision Process (MDP) have greatly advanced the field of single-agent control, application of similar ideas to multi-agent domains has proven problematic. The advantages of such an approach over traditional heuristic and experimental models...
| Main Author: | |
|---|---|
| Language: | ENG |
| Published: |
ScholarWorks@UMass Amherst
2006
|
| Subjects: | |
| Online Access: | https://scholarworks.umass.edu/dissertations/AAI3242298 |