Seq2Seq Mimic Games: A Signaling Perspective
This work addresses communication emergence in adversarial AI settings, but it appears incremental as it builds on existing Seq2Seq and signaling concepts without claiming major breakthroughs.
The paper tackles the problem of how sequence-to-sequence models can learn to communicate in multiagent adversarial games inspired by the Imitation game, proposing a modeling approach and initial experiments with signaling theory analysis.
We study the emergence of communication in multiagent adversarial settings inspired by the classic Imitation game. A class of three player games is used to explore how agents based on sequence to sequence (Seq2Seq) models can learn to communicate information in adversarial settings. We propose a modeling approach, an initial set of experiments and use signaling theory to support our analysis. In addition, we describe how we operationalize the learning process of actor-critic Seq2Seq based agents in these communicational games.