mlsanityData to 7 Oct 2026

Learning to Share in Multi-Agent Reinforcement Learning

arXiv 2112.08702 ↗First posted 16 Dec 2021cs.LG cs.MAcited by 4

Not on the map. Why?

Abstract (arXiv)

In this paper, we study the problem of networked multi-agent reinforcement learning (MARL), where a number of agents are deployed as a partially connected network and each interacts only with nearby agents. Networked MARL requires all agents to make decisions in a decentralized manner to optimize a global objective with restricted communication between neighbors over the network. Inspired by the fact that sharing plays a key role in human's learning of cooperation, we propose LToS, a hierarchically decentralized MARL framework that enables agents to learn to dynamically share reward with neighbors so as to encourage agents to cooperate on the global objective through collectives. For each agent, the high-level policy learns how to share reward with neighbors to decompose the global objective, while the low-level policy learns to optimize the local objective induced by the high-level policies in the neighborhood. The two policies form a bi-level optimization and learn alternately. We empirically demonstrate that LToS outperforms existing methods in both social dilemma and networked MARL scenarios across scales.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 35 of its 54 references that are in the map. First posted on arXiv 16 Dec 2021.

Builds on

35 of 54 references.

References · 35

  1. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  2. 2015Continuous control with deep reinforcement learningcited by 3,279
  3. 2018DARTS: Differentiable Architecture Searchcited by 1,782
  4. 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,519
  5. 2017Counterfactual Multi-Agent Policy Gradientscited by 733
  6. 2018QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learningcited by 697
  7. 2015Deep Recurrent Q-Learning for Partially Observable MDPscited by 457
  8. 2019QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learningcited by 372
  9. 2020QPLEX: Duplex Dueling Multi-Agent Q-Learningcited by 267
  10. 2018Actor-Attention-Critic for Multi-Agent Reinforcement Learningcited by 259
  11. 2018Fully Decentralized Multi-Agent Reinforcement Learning with Networked Agentscited by 189
  12. 2019MAVEN: Multi-Agent Variational Explorationcited by 181
23 more
  1. 2018Graph Convolutional Reinforcement Learningcited by 148
  2. 2019CoLight: Learning Network-level Cooperation for Traffic Signal Controlcited by 133
  3. 2019CityFlow: A Multi-Agent Reinforcement Learning Environment for Large Scale City Traffic Scenariocited by 114
  4. 2018Inequity aversion improves cooperation in intertemporal social dilemmascited by 106
  5. 2019Deep Coordination Graphscited by 96
  6. 2019Learning to Schedule Communication in Multi-agent Reinforcement Learningcited by 89
  7. 2020Qatten: A General Framework for Cooperative Multiagent Reinforcement Learningcited by 81
  8. 2019Shapley Q-value: A Local Reward Approach to Solve Global Reward Gamescited by 71
  9. 2017MAgent: A Many-Agent Reinforcement Learning Platform for Artificial Collective Intelligencecited by 69
  10. 2017A multi-agent reinforcement learning model of common-pool resource appropriationcited by 68
  11. 2020Learning to Incentivize Other Learning Agentscited by 55
  12. 2020Learning Individually Inferred Communication for Multi-Agent Cooperationcited by 55
  13. 2020Multi-agent Reinforcement Learning for Networked System Controlcited by 51
  14. 2017Prosocial learning agents solve generalized Stag Hunts better than selfish onescited by 47
  15. 2020Scalable Multi-Agent Reinforcement Learning for Networked Systems with Average Rewardcited by 46
  16. 2019Diagnosing Reinforcement Learning for Traffic Signal Controlcited by 33
  17. 2019Learning Reciprocity in Complex Sequential Social Dilemmascited by 24
  18. 2017Consequentialist conditional cooperation in social dilemmas with imperfect informationcited by 23
  19. 2019Value Propagation for Decentralized Networked Deep Multi-agent Reinforcement Learningcited by 17
  20. 2021Divergence-Regularized Multi-Agent Actor-Criticcited by 15
  21. 2019Analysing Factorizations of Action-Value Networks for Cooperative Multi-Agent Reinforcement Learningcited by 12
  22. 2019Coordinating the Crowd: Inducing Desirable Equilibria in Non-Cooperative Systemscited by 11
  23. 2017Decentralized and Distributed Temperature Control via HVAC Systems in Energy Efficient Buildingscited by 3

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 2; 2025: 1.

4 papers.

  1. 2024Learning to Balance Altruism and Self-interest Based on Empathy in Mixed-Motive Gamescited by 6
  2. 2023Learning Roles with Emergent Social Value Orientationscited by 2
  3. 2025Dynamic Pricing in High-Speed Railways Using Multi-Agent Reinforcement Learningcited by 1
  4. 2024Achieving Collective Welfare in Multi-Agent Reinforcement Learning via Suggestion Sharingcited by 0