On Equivalence Between Decentralized Policy-Profile Mixtures and Behavioral Coordination Policies in Multi-Agent Systems
Preprint
Abstract
Constrained decentralized team problem formulations are good models for many cooperative multi-agent systems. Constraints necessitate randomization when solving for optimal solutions -- our past results show that joint randomization amongst the team is necessary for (strong) Lagrangian duality to hold -- , but a better understanding of randomization still remains. For a partially observed multi-agent system with Borel hidden state and finite observations and actions, we prove the equivalence between joint mixtures of decentralized policy-profiles (both pure and behavioral) and common-information based behavioral coordination policies (also mixtures of them). This generalizes past work that shows equivalence between pure decentralized policy-profiles and pure coordination policies. The equivalence can be exploited to develop results on strong duality and number of randomizations.Keywords
All Related Versions
This publication has 11 references indexed in Scilit:
- The Common-Information Approach to Decentralized Stochastic Control2014
- Decentralized Stochastic Control with Partial History Sharing: A Common Information ApproachIEEE Transactions on Automatic Control, 2013
- Optimal Control Strategies in Delayed Sharing Information StructuresIEEE Transactions on Automatic Control, 2010
- Common randomness and distributed control: A counterexampleSystems & Control Letters, 2007
- Information and Strategies in Dynamic GamesSIAM Journal on Control and Optimization, 1992
- A convex analytic approach to Markov decision processesProbability Theory and Related Fields, 1988
- Optimal causal coding - decoding problemsIEEE Transactions on Information Theory, 1983
- On the Structure of Real-Time Source CodersBell System Technical Journal, 1979
- A standard form for sequential stochastic controlTheory of Computing Systems, 1973
- 11. Extensive Games and the Problem of Information1953