Group-Agent Reinforcement Learning with Heterogeneous Agents
On the map: Deep reinforcement learning methods → RL for games and combinatorial optimization
Abstract (arXiv)
Group-agent reinforcement learning (GARL) is a newly arising learning scenario, where multiple reinforcement learning agents study together in a group, sharing knowledge in an asynchronous fashion. The goal is to improve the learning performance of each individual agent. Under a more general heterogeneous setting where different agents learn using different algorithms, we advance GARL by designing novel and effective group-learning mechanisms. They guide the agents on whether and how to learn from action choices from the others, and allow the agents to adopt available policy and value function models sent by another agent if they perform better. We have conducted extensive experiments on a total of 43 different Atari 2600 games to demonstrate the superior performance of the proposed method. After the group learning, among the 129 agents examined, 96% are able to achieve a learning speed-up, and 72% are able to learn over 100 times faster. Also, around 41% of those agents have achieved a higher accumulated reward score by learning in less than 5% of the time steps required by a single agent when learning on its own.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL for games and combinatorial optimization, one of 15 directions in Deep reinforcement learning methods. Builds on 20 of its 41 references that are in the map. First posted on arXiv 21 Jan 2025.
Builds on
20 of 41 references.
References · 20
- 2017Proximal Policy Optimization Algorithmscited by 15,215
- 2013Playing Atari with Deep Reinforcement Learningcited by 3,274
- 2016Asynchronous Methods for Deep Reinforcement Learningcited by 2,258
- 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,558
- 2019Mastering Atari, Go, Chess and Shogi by Planning with a Learned Modelcited by 1,353
- 2018QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learningcited by 708
- 2016Deep Exploration via Bootstrapped DQNcited by 527
- 2016Learning Multiagent Communication with Backpropagationcited by 366
- 2016Safe and Efficient Off-Policy Reinforcement Learningcited by 264
- 2016Sample Efficient Actor-Critic with Experience Replaycited by 188
- 2019MAVEN: Multi-Agent Variational Explorationcited by 185
- 2020SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement Learningcited by 152
8 more
- 2020ROMA: Multi-Agent Reinforcement Learning with Emergent Rolescited by 137
- 2020Shared Experience Actor-Critic for Multi-Agent Reinforcement Learningcited by 116
- 2016Averaged-DQN: Variance Reduction and Stabilization for Deep Reinforcement Learningcited by 106
- 2017Multiagent Bidirectionally-Coordinated Nets: Emergence of Human-level Coordination in Learning to Play StarCraft Combat Gamescited by 96
- 2019Value Propagation for Decentralized Networked Deep Multi-agent Reinforcement Learningcited by 19
- 2020SEERL: Sample Efficient Ensemble Reinforcement Learningcited by 11
- 2022FCMNet: Full Communication Memory Net for Team-Level Cooperation in Multi-Agent Systemscited by 7
- 2022Group-Agent Reinforcement Learningcited by 1
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2024Group-Aware Coordination Graph for Multi-Agent Reinforcement Learning
- 2025Group-in-Group Policy Optimization for LLM Agent Training
- 2026GARL: Game-Theoretic Reinforcement Learning for Multi-Agent Strategic Prioritisation
- 2026Group-Graph Policy Optimization for Long-Horizon Agentic Reinforcement Learning
- 2025IPPO Learns the Game, Not the Team: A Study on Generalization in Heterogeneous Agent Teams
- 2024The impact of behavioral diversity in multi-agent reinforcement learning
- 2025End-to-End Optimization of LLM-Driven Multi-Agent Search Systems via Heterogeneous-Group-Based Reinforcement Learning
- 2025LLM Collaboration With Multi-Agent Reinforcement Learning