mlsanityData to 14 Oct 2026

Recursive Reasoning Graph for Multi-Agent Reinforcement Learning

arXiv 2203.02844 ↗First posted 6 Mar 2022cs.LG cs.AI cs.MAcited by 2

Not on the map. Why?

Abstract (arXiv)

Multi-agent reinforcement learning (MARL) provides an efficient way for simultaneously learning policies for multiple agents interacting with each other. However, in scenarios requiring complex interactions, existing algorithms can suffer from an inability to accurately anticipate the influence of self-actions on other agents. Incorporating an ability to reason about other agents' potential responses can allow an agent to formulate more effective strategies. This paper adopts a recursive reasoning model in a centralized-training-decentralized-execution framework to help learning agents better cooperate with or compete against others. The proposed algorithm, referred to as the Recursive Reasoning Graph (R2G), shows state-of-the-art performance on multiple multi-agent particle and robotics games.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 18 of its 30 references that are in the map. First posted on arXiv 6 Mar 2022.

Builds on

18 of 30 references.

References · 18

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2017Graph Attention Networkscited by 8,923
  3. 2017Inductive Representation Learning on Large Graphscited by 6,320
  4. 2015Continuous control with deep reinforcement learningcited by 3,407
  5. 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,558
  6. 2018Soft Actor-Critic Algorithms and Applicationscited by 1,240
  7. 2017Rainbow: Combining Improvements in Deep Reinforcement Learningcited by 786
  8. 2017Counterfactual Multi-Agent Policy Gradientscited by 751
  9. 2018QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learningcited by 708
  10. 2018Residual Reinforcement Learning for Robot Controlcited by 274
  11. 2017Autonomous Agents Modelling Other Agents: A Comprehensive Survey and Open Problemscited by 131
  12. 2017Continuous Adaptation via Meta-Learning in Nonstationary and Competitive Environmentscited by 108
6 more
  1. 2016Opponent Modeling in Deep Reinforcement Learningcited by 97
  2. 2019Probabilistic Recursive Reasoning for Multi-Agent Reinforcement Learningcited by 68
  3. 2018CM3: Cooperative Multi-goal Multi-stage Multi-agent Reinforcement Learningcited by 31
  4. 2018Multiagent Soft Q-Learningcited by 26
  5. 2019Modelling Bounded Rationality in Multi-Agent Interactions by Generalized Recursive Reasoningcited by 24
  6. 2019Interaction-Aware Multi-Agent Reinforcement Learning for Mobile Agents with Individual Goalscited by 3

Built on by

Cited by year

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

2 papers.

  1. 2024Graph Q-Learning for Combinatorial Optimizationcited by 1
  2. 2025Local Pairwise Distance Matching for Backpropagation-Free Reinforcement Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Reinforcement Networks: novel framework for collaborative Multi-Agent Reinforcement Learning tasks
  2. 2026Recursive Agent Optimization
  3. 2025Multi-Task Multi-Agent Reinforcement Learning via Skill Graphs
  4. 2026Strat-Reasoner: Reinforcing Strategic Reasoning of LLMs in Multi-Agent Games
  5. 2026Recursive Multi-Agent Systems
  6. 2025Explaining Decentralized Multi-Agent Reinforcement Learning Policies
  7. 2025A Roadmap Towards Improving Multi-Agent Reinforcement Learning With Causal Discovery And Inference
  8. 2025DRAFT-RL: Multi-Agent Chain-of-Draft Reasoning for Reinforcement Learning-Enhanced LLMs