An In-depth Analysis Of Discretization Methods For Communication Learning Using Backpropagation With Multi-agent Reinforcement Learning

Abstract

Communication is crucial in multi-agent reinforcement learning when agents are not able to observe the full state of the environment. The most common approach to allow learned communication between agents is the use of a differentiable communication channel that allows gradients to flow between agents as a form of feedback. However, this is challenging when we want to use discrete messages to reduce the message size, since gradients cannot flow through a discrete communication channel. Previous work proposed methods to deal with this problem. However, these methods are tested in different communication learning architectures and environments, making it hard to compare them. In this paper, we compare several state-of-the-art discretization methods as well as a novel approach. We do this comparison in the context of communication learning using gradients from other agents and perform tests on several environments. In addition, we present COMA-DIAL, a communication learning approach based

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyvanneste2023an

Related papers

• An Analysis Of Discretization Methods For Communication Learning With Multi-agent Reinforcement Learning (2022)0.00
• Learning What To Say And How Precisely: Efficient Communication Via Differentiable Discrete Communication Learning (2025)0.00
• Mixed Cooperative-competitive Communication Using Multi-agent Reinforcement Learning (2021)5.84
• Rgmcomm: Return Gap Minimization Via Discrete Communications In Multi-agent Reinforcement Learning (2023)6.77
• Learning Emergent Discrete Message Communication For Cooperative Reinforcement Learning (2021)5.24
• A Survey Of Multi-agent Deep Reinforcement Learning With Communication (2022)0.00
• Learning Practical Communication Strategies In Cooperative Multi-agent Reinforcement Learning (2022)0.00
• Multi-agent Reinforcement Learning With Communication-constrained Priors (2025)0.00