Fig. 9: An example of agent-based task selection for a model with two adapters, A1 and A2.
From: Building adaptive knowledge bases for evolving continual learning models
A new batch with class \({{\mathcal{Y}}}^{t}\), is encountered. The task similarity for each adapter is calculated using buffers of previously learned examples \({{\mathcal{B}}}_{1}\) and \({{\mathcal{B}}}_{2}\). A critic is trained based on model performance and provides feedback to the policy, which provides an action for the given state of task similarities. The action identifies the adapter best suited to training on examples with class \({{\mathcal{Y}}}^{t}\) based on the current state of the model.
