# Multi-Agent Reinforcement Learning for Problems with Combined Individual and Team Reward

arXiv: https://arxiv.org/abs/2003.10598 · HTML: https://mlsanity.com/paper/2003.10598/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Mar 2020.

## Built on by (most cited first, 8 of 8)

- [Deep Multiagent Reinforcement Learning: Challenges and Directions](https://mlsanity.com/paper/2106.15691/) (2021)
- [Stronger-MAS: Multi-Agent Reinforcement Learning for Collaborative LLMs](https://mlsanity.com/paper/2510.11062/) (2025)
- [AoI-Aware Resource Allocation for Platoon-Based C-V2X Networks via Multi-Agent Multi-Task Reinforcement Learning](https://mlsanity.com/paper/2105.04196/) (2021)
- [Curiosity-driven Exploration in Sparse-reward Multi-agent Reinforcement Learning](https://mlsanity.com/paper/2302.10825/) (2023)
- [Promoting Cooperation in Multi-Agent Reinforcement Learning via Mutual Help](https://mlsanity.com/paper/2302.09277/) (2023)
- [Radio Resource Management and Path Planning in Intelligent Transportation Systems via Reinforcement Learning for Environmental Sustainability](https://mlsanity.com/paper/2405.08053/) (2024)
- [Scaling up Energy-Aware Multi-Agent Reinforcement Learning for Mission-Oriented Drone Networks with Individual Reward](https://mlsanity.com/paper/2605.24992/) (2026)
- [ICMAPE: In-Context Multiagent Pure Exploration](https://mlsanity.com/paper/2609.33986/) (2026)

## Abstract (arXiv)

Many cooperative multi-agent problems require agents to learn individual tasks while contributing to the collective success of the group. This is a challenging task for current state-of-the-art multi-agent reinforcement algorithms that are designed to either maximize the global reward of the team or the individual local rewards. The problem is exacerbated when either of the rewards is sparse leading to unstable learning. To address this problem, we present Decomposed Multi-Agent Deep Deterministic Policy Gradient (DE-MADDPG): a novel cooperative multi-agent reinforcement learning framework that simultaneously learns to maximize the global and local rewards. We evaluate our solution on the challenging defensive escort team problem and show that our solution achieves a significantly better and more stable performance than the direct adaptation of the MADDPG algorithm.