Improving Cooperation in Language Games with Bayesian Inference and the Cognitive Hierarchy

TL;DR

This paper introduces a Bayesian approach to improve cooperation in language games by modeling semantic and pragmatic uncertainties, leading to better agent performance in cooperative tasks like Codenames.

Contribution

It combines Bayesian inference with the cognitive hierarchy to handle multiple uncertainty types in language games, advancing cooperative AI strategies.

Findings

Bayesian agents outperform baseline in uncertain semantics scenarios

Modeling both semantic and pragmatic uncertainties improves cooperation

Agents adapt better to partner behavior through Bayesian learning

Abstract

In two-player cooperative games, agents can play together effectively when they have accurate assumptions about how their teammate will behave, but may perform poorly when these assumptions are inaccurate. In language games, failure may be due to disagreement in the understanding of either the semantics or pragmatics of an utterance. We model coarse uncertainty in semantics using a prior distribution of language models and uncertainty in pragmatics using the cognitive hierarchy, combining the two aspects into a single prior distribution over possible partner types. Fine-grained uncertainty in semantics is modeled using noise that is added to the embeddings of words in the language. To handle all forms of uncertainty we construct agents that learn the behavior of their partner using Bayesian inference and use this information to maximize the expected value of a heuristic function. We test this approach by constructing Bayesian agents for the game of Codenames, and show that they perform better in experiments where semantics is uncertain