Seq2Seq Mimic Games: A Signaling Perspective

Abstract

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.

arXiv commentNIPS 2018 Workshop on Emergent Communication (accepted)

References in corpus (14)

• Adam: A Method for Stochastic Optimization
• Sequence to Sequence Learning with Neural Networks
• Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
• Categorical Reparameterization with Gumbel-Softmax
• A Neural Conversational Model
• Learning to Communicate with Deep Multi-Agent Reinforcement Learning
• SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient
• GANS for Sequences of Discrete Elements with the Gumbel-softmax Distribution
• Adversarial Evaluation of Dialogue Models
• Emergence of Language with Multi-agent Games: Learning to Communicate with Sequences of Symbols
• Emergent Communication through Negotiation
• Data Generation as Sequential Decision Making
• Stochastic Backpropagation through Mixture Density Distributions
• Proximal Policy Optimization and its Dynamic Version for Sequence Generation