Blind interactive learning of modulation schemes: Multi-agent cooperation without co-design

Abstract

We examine the problem of learning to cooperate in the context of wireless communication. In our setting, two agents must learn modulation schemes that enable them to communicate across a power-constrained additive white Gaussian noise channel. We investigate whether learning is possible under different levels of information sharing between distributed agents which are not necessarily co-designed. We employ the "Echo" protocol, a "blind" interactive learning protocol where an agent hears, understands, and repeats (echoes) back the message received from another agent, simultaneously training itself to communicate. To capture the idea of cooperation between "not necessarily co-designed" agents we use two different populations of function approximators - neural networks and polynomials. We also include interactions between learning agents and non-learning agents with fixed modulation protocols such as QPSK and 16QAM. We verify the universality of the Echo learning approach, showing it succeeds independent of the inner workings of the agents. In addition to matching the communication expectations of others, we show that two learning agents can collaboratively invent a successful communication approach from independent random initializations. We complement our simulations with an implementation of the Echo protocol in software-defined radios. To explore the continuum of co-design, we study how learning is impacted by different levels of information sharing between agents, including sharing training symbols, losses, and full gradients. We find that co-design (increased information sharing) accelerates learning. Learning higher order modulation schemes is a more difficult task, and the beneficial effect of co-design becomes more pronounced as the task becomes harder.

arXiv comment33 pages, 25 figures, code can be found at https://github.com/ml4wireless/echo, accepted for publication in IEEE Access

References in corpus (18)

• Adam: A Method for Stochastic Optimization
• The NumPy array: a structure for efficient numerical computation
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Playing Atari with Deep Reinforcement Learning
• Deep Joint Source-Channel Coding for Wireless Image Transmission
• Learning to Communicate with Deep Multi-Agent Reinforcement Learning
• Deep Learning-Based Communication Over the Air
• End-to-end Deep Learning of Optical Fiber Communications
• Fully Decentralized Multi-Agent Reinforcement Learning with Networked Agents
• Sensitivity and Generalization in Neural Networks: an Empirical Study
• Modeling Others using Oneself in Multi-Agent Reinforcement Learning
• Convolutional Radio Modulation Recognition Networks
• Cooperative Multi-Agent Reinforcement Learning for Low-Level Wireless Communication
• An End-to-End Block Autoencoder For Physical Layer Based On Neural Networks
• Deep Learning based End-to-End Wireless Communication Systems with Conditional GAN as Unknown Channel
• Achievable Information Rates for Nonlinear Fiber Communication via End-to-end Autoencoder Learning
• Joint Transceiver Optimization for Wireless Communication PHY with Convolutional Neural Network
• Neural Lattice Decoders