Making Friends on the Fly- Advances in Ad Hoc Teamwork
Table 3.1 Example of play in the bandit domain. . . . . . . . . . . . . . . . . . 35
Table 3.2 TeamK and reactivity for various settings in the bandit
domain given that the ad hoc agent believes
that its teammates are drawn from {ε-greedy, UCB(c)} . . . . . . 38
Table 3.3 TeamK and reactivity for various settings in the pursuit
domain . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 41
Table 3.4 Ranges of the dimensions for scenarios in the 3 domains
used in this book . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 46
Table 4.1 This table shows existing research into ad hoc teamwork
and what types of problems they address. . . . . . . . . . . . . . . . 58
Table 6.1 Problems that are solvable in polynomial time . . . . . . . . . . . . 88
Table 7.1 An overview of the experiments described in this chapter.
We denote hand-coded by HC, Externally-created
by Ext., and parameterized by Param . . . . . . . . . . . . . . . . . . 96
Table 7.2 Features for predicting a teammate’s actions . . . . . . . . . . . . . 104
xiii