Title | ||
---|---|---|
Team behavior in interactive dynamic influence diagrams with applications to ad hoc teams. |
Abstract | ||
---|---|---|
Planning for ad hoc teamwork is challenging because it involves individual agents collaborating with others without any prior coordination. However, individual decision making in multiagent settings faces the task of having to reason about other agents' actions, which in turn involves reasoning about others. An established approximation that operationalizes this approach is to bound the infinite nesting from below by introducing level 0 models, which results in suboptimal team solutions in cooperative settings. We demonstrate this limitation and mitigate it by integrating learning into planning. The augmented framework is applied to ad hoc teamwork. |
Year | DOI | Venue |
---|---|---|
2014 | 10.5555/2615731.2616061 | AAMAS |
Keywords | DocType | Volume |
team behavior,interactive dynamic influence diagram,suboptimal team solution,cooperative setting,multiagent setting,individual agent,augmented framework,established approximation,individual decision,prior coordination,reinforcement learning | Journal | abs/1409.0302 |
Citations | PageRank | References |
2 | 0.37 | 13 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Muthukumaran Chandrasekaran | 1 | 32 | 4.81 |
Prashant Doshi | 2 | 926 | 90.23 |
Yifeng Zeng | 3 | 415 | 43.27 |
Yingke Chen | 4 | 52 | 4.78 |