Narrow Results

Distillations utilize multi-agent based modeling and simulation techniques to study warfare as a complex adaptive system at the conceptual level. The focus is placed on the interactions between the agents to facilitate study of cause and effect between individual interactions and overall system behavior. Current distillations do not utilize machine-learning techniques to model the cognitive abilities of individual combatants but employ agent control paradigms to represent agents as highly instinctual entities. For a team of agents implementing a reinforcement-learning paradigm, the rate of learning is not sufficient for agents to adapt to this hostile environment. However, by allowing the agents to communicate their respective rewards for actions performed as the simulation progresses, the rate of learning can be increased sufficiently to significantly increase the teams chances of survival. This paper presents the results of trials to measure the success of a team-based approach to the reinforcement-learning problem in a distillation, using reward communication to increase learning rates.

In this paper, the regression learning algorithm with vector-valued RKHS is studied. We motivate the need for extending learning theory of scalar-valued functions and analze the learning performance. In this setting, the output data are from a Hilbert space $Y$, the associated RKHS consists of functions with values lie in $Y$. By providing mathematical aspects of vector-valued integral operator $L_K$, the capacity independent error bounds and learning rates are derived by means of the integral operator technique.

We consider the coefficient-based least squares regularized regression learning algorithm for the strongly and uniformly mixing samples. We obtain the capacity independent error bounds of the algorithm by means of the integral operator techniques. A standard assumption in theoretical study of learning algorithms for regression is the uniform boundedness of output sample values. We abandon this boundedness assumption and carry out the error analysis with output sample values satisfying a generalized moment hypothesis.

In this paper, we study the performance of kernel-based regression learning with non-iid sampling. The non-iid samples are drawn from different probability distributions with the same conditional distribution. A more general marginal distribution assumption is proposed. Under this assumption, the consistency of the regularization kernel network (RKN) and the coefficient regularization kernel network (CRKN) are proved. Satisfactory capacity independently error bounds and learning rates are derived by the techniques of integral operator.

We study distributed learning with partial coefficients regularization scheme in a reproducing kernel Hilbert space (RKHS). The algorithm randomly partitions the sample set ${\{z_i\}}_{i=1}^N$ into $m$ disjoint sample subsets of equal size. In order to reduce the complexity of algorithms, we apply a partial coefficients regularization scheme to each sample subset to produce an output function, and average the individual output functions to get the final global estimator. The error bound in the $L^2$-metric is deduced and the asymptotic convergence for this distributed learning with partial coefficients regularization is proved by the integral operator technique. Satisfactory learning rates are then derived under a standard regularity condition on the regression function, which reveals an interesting phenomenon that when $m\le N^s$ and $s$ is small enough, this distributed learning has the same convergence rate with the algorithm processing the whole data in one single machine.

This study explores whether characteristics of the collaboration structure in software development teams affect development learning rates, with a secondary goal of testing product complexity as a moderator. We develop suitable hypotheses under the theoretical lens of cognitive load theory. The empirical study uses archival data on an ordinary least squares model to find significant associations between collaboration structure, product complexity and the learning rates exhibited by 230 development teams producing open source software. Results show two distinct subgroups of projects: The first subgroup exhibits an average 78% learning rate, and the other subgroup “unlearned”, i.e., productivity deteriorated over time instead of improved. In the learning subgroup, collaboration network density negatively impacted learning, while product complexity interacted with collaboration network centralisation and boundary spanning activity. In the unlearning subgroup, only network density impacted learning rates and no moderating effects were found. Practical implications and future opportunities for research are discussed.