Pragmatic Reasoning in Structured Signaling Games
This work addresses communication efficiency in artificial agents, offering incremental improvements over existing pragmatic reasoning frameworks.
The paper tackles the problem of pragmatic reasoning in structured signaling games by introducing structured-RSA (sRSA), showing that agents using sRSA achieve efficiency near the information theoretic limit after 1-2 recursion levels and develop communication closer to this frontier compared to baseline methods.
In this work we introduce a structured signaling game, an extension of the classical signaling game with a similarity structure between meanings in the context, along with a variant of the Rational Speech Act (RSA) framework which we call structured-RSA (sRSA) for pragmatic reasoning in structured domains. We explore the behavior of the sRSA in the domain of color and show that pragmatic agents using sRSA on top of semantic representations, derived from the World Color Survey, attain efficiency very close to the information theoretic limit after only 1 or 2 levels of recursion. We also explore the interaction between pragmatic reasoning and learning in multi-agent reinforcement learning framework. Our results illustrate that artificial agents using sRSA develop communication closer to the information theoretic frontier compared to agents using RSA and just reinforcement learning. We also find that the ambiguity of the semantic representation increases as the pragmatic agents are allowed to perform deeper reasoning about each other during learning.