# Value-Decomposition Networks For Cooperative Multi-Agent Learning

## TL;DR

This paper introduces value-decomposition networks for cooperative multi-agent reinforcement learning, effectively addressing partial observability and spurious rewards, leading to improved team performance in complex environments.

## Contribution

The paper proposes a novel value decomposition network architecture that decomposes team value functions into individual agent values, enhancing learning in partially observable multi-agent settings.

## Key findings

- Value decomposition improves learning performance.
- Combining with weight sharing and role info enhances results.
- Outperforms traditional methods in various domains.

## Abstract

We study the problem of cooperative multi-agent reinforcement learning with a single joint reward signal. This class of learning problems is difficult because of the often large combined action and observation spaces. In the fully centralized and decentralized approaches, we find the problem of spurious rewards and a phenomenon we call the "lazy agent" problem, which arises due to partial observability. We address these problems by training individual agents with a novel value decomposition network architecture, which learns to decompose the team value function into agent-wise value functions. We perform an experimental evaluation across a range of partially-observable multi-agent domains and show that learning such value-decompositions leads to superior results, in particular when combined with weight sharing, role information and information channels.