Title | ||
---|---|---|
Iterative Online Planning in Multiagent Settings with Limited Model Spaces and PAC Guarantees |
Abstract | ||
---|---|---|
Methods for planning in multiagent settings often model other agents' possible behaviors. However, the space of these models - whether these are policy trees, finite-state controllers or intentional models - is very large and thus arbitrarily bounded. This may exclude the true model or the optimal model. In this paper, we present a novel iterative algorithm for online planning that considers a limited model space, updates it dynamically using data from interactions, and provides a provable and probabilistic bound on the approximation error. We ground this approach in the context of graphical models for planning in partially observable multiagent settings - interactive dynamic influence diagrams. We empirically demonstrate that the limited model space facilitates fast solutions and that the true model often enters the limited model space. |
Year | DOI | Venue |
---|---|---|
2015 | 10.5555/2772879.2773298 | Autonomous Agents and Multi-Agent Systems |
Keywords | Field | DocType |
online planning, multiple agents, influence diagram, mental models | Observable,Iterative method,Computer science,Influence diagram,Artificial intelligence,Graphical model,Probabilistic logic,Machine learning,Approximation error,Bounded function | Conference |
Citations | PageRank | References |
4 | 0.43 | 21 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yingke Chen | 1 | 52 | 4.78 |
Prashant Doshi | 2 | 926 | 90.23 |
Yifeng Zeng | 3 | 415 | 43.27 |