Understanding Early Word Learning in Situated Artificial Agents
This work addresses the problem of understanding grounded language learning mechanisms in artificial agents, which is incremental as it applies existing methods to analyze learning effects without achieving new performance benchmarks.
The paper investigates how simple neural network agents learn to interpret single-word instructions in a simulated 3D world, using policy-gradient training and insights from developmental psychology to analyze emergent biases and propose a visualization method for semantic representations.
Neural network-based systems can now learn to locate the referents of words and phrases in images, answer questions about visual scenes, and execute symbolic instructions as first-person actors in partially-observable worlds. To achieve this so-called grounded language learning, models must overcome challenges that infants face when learning their first words. While it is notable that models with no meaningful prior knowledge overcome these obstacles, researchers currently lack a clear understanding of how they do so, a problem that we attempt to address in this paper. For maximum control and generality, we focus on a simple neural network-based language learning agent, trained via policy-gradient methods, which can interpret single-word instructions in a simulated 3D world. Whilst the goal is not to explicitly model infant word learning, we take inspiration from experimental paradigms in developmental psychology and apply some of these to the artificial agent, exploring the conditions under which established human biases and learning effects emerge. We further propose a novel method for visualising semantic representations in the agent.