In this paper we present a novel method for a naive agent to detect novel objects it encounters in an interaction. We train a reinforcement learning policy on a stacking task given a known object type, and then observe the results of the agent attempting to stack various other objects based on the same trained policy. By extracting embedding vectors from a convolutional neural net trained over the results of the aforementioned stacking “play,” we can determine the similarity of a given object to known object types, and determine if the given object is likely dissimilar enough to the known types to be considered a novel class of object. We present the results of this method on two datasets gathered using two different policies and demonstrate what information the agent needs to extract from its environ- ment to make these novelty judgments.

We offer philosophical motivations for a method we call Virtual World Cognitive Science (VW CogSci), in which re- searchers use virtual embodied agents that are embedded in virtual worlds to explore questions in the field of Cognitive Science. We focus on questions about mental and linguistic representation and the ways that such computational modeling can add rigor to philosophical thought experiments, as well as the terminology used in the scientific study of such representations. We find that this method forces researchers to take a god's-eye view when describing dynamical relationships be- tween entities in minds and entities in an environment in a way that eliminates the need for problematic talk of belief and concept *types*, such as *the belief that cats are silly*, and *the concept CAT*, while preserving belief and concept *tokens* in individual cognizers' minds. We conclude with some further key advantages of VW CogSci for the scientific study of mental and linguistic representation and for Cognitive Science more broadly.

It takes children considerable learning and development to accurately predict whether an object is safely balanced or will fall -- something that happens if its center of mass is not supported from below. In the meantime, children go through a characteristic set of mistaken beliefs. Here we use an adapted version of the classical balance task to evaluate whether different models go through the same stages. Preliminary results show that convolutional neural networks (CNNs) do learn the task but do not necessarily go through the same stages. We are also testing several simulation-based accounts. We anticipate completing this work in time for the conference. The findings will help clarify the space of possible accounts of children's acquisition of intuitions about gravity and balance.