USC-Coordinators ProjectPeople |
|
Research Summary
We are working on a project known as Coordinators in collaboration with Honeywell Laboratories. Currently, our work is focused around applying decision theoretic techniques to Adjustable Autonomy.
Key papers:
- J. Marecki, M. Tambe,"On Opportunistic Techniques for Solving the Decentralized MDP with Temporal Constraints In Proceedings of the 6th International Joint Conference on Autonomous Agents and Multi-agent Systems (AAMAS), 2007
- Janusz Marecki, Sven Koenig, Milind Tambe "A Fast Analytical Algorithm for Solving Markov Decision Processes with Continuous Resources” In Proceedings of the 20th International Joint Conference on Artificial Intelligence (IJCAI), 2007
- R. Nair, P. Varakantham, M. Tambe, M. Yokoo "Networked Distributed POMDPs: A Synthesis of Distributed Constraint Optimization and POMDPs” In AAAI-05: Proceedings of the Twentieth National Conference on Artificial Intelligence, July 2005
- P. Varakantham, R. Nair, M. Tambe, M. Yokoo "Winning back the CUP for Distributed POMDPs: Planning over continuous belief spaces In AAMAS-06: Proceedings of the fifth International Conference on Autonomous Agents and Multiagent Systems, May 2006
- J. Marecki, Z. Topol, M. Tambe,"A Fast Analytical Algorithm for MDPs with Continuous State Spaces In Proceedings of 8th Workshop on Game Theoretic and Decision Theoretic Agents at AAMAS 2006
Adjustable Autonomy
Adjustable autonomy (AA) encompasses the strategies by which an agent selects the appropriate entity (itself, a human user, or another agent) to make a decision at key moments when an action is required. Our initial work on AA for Coordinators has focused on the use of Markov Decision Processes (MDPs) to account for the uncertainties in the domain.
Background work:
- P. Scerri, D.V. Pynadath and M. Tambe, 2002. "Towards Adjustable Autonomy for the Real World," in Journal of Artificial Intelligence Research, Volume 17, pp. 171-228, 2002.