A framework for the emergence and analysis of language in social learning agents
This work addresses the challenge of representational invariance and generalization in AI models, particularly for social learning agents, but it appears incremental as it builds on existing reinforcement learning and communication frameworks.
The study tackled the problem of improving generalization in artificial neural networks by proposing a communication protocol between cooperative agents to mimic language features, resulting in a higher goal-finding rate and better generalization across tasks.
Artificial neural networks (ANNs) are increasingly used as research models, but questions remain about their generalizability and representational invariance. Biological neural networks under social constraints evolved to enable communicable representations, demonstrating generalization capabilities. This study proposes a communication protocol between cooperative agents to analyze the formation of individual and shared abstractions and their impact on task performance. This communication protocol aims to mimic language features by encoding high-dimensional information through low-dimensional representation. Using grid-world mazes and reinforcement learning, teacher ANNs pass a compressed message to a student ANN for better task completion. Through this, the student achieves a higher goal-finding rate and generalizes the goal location across task worlds. Further optimizing message content to maximize student reward improves information encoding, suggesting that an accurate representation in the space of messages requires bi-directional input. This highlights the role of language as a common representation between agents and its implications on generalization capabilities.