mlsanityData to 14 Oct 2026

Multi-agent reinforcement learning

182 papers0 this weekLow confidence in this grouping: the papers may belong to more than one topic, or the group may changeLow confidence in this grouping: the papers may belong to more than one topic, or the group may change · About

Keywords: multi-agent, marl, agents, multi-agent reinforcement, games

Key facts. Multi-agent reinforcement learning: 182 papers on arXiv since 2024 (data through 14 Oct 2026). 3 of its 182 mapped papers (2%) cite “When is Mean-Field Reinforcement Learning Tractable and Relevant?” (2024, arXiv 2402.05757). 3 new papers 30 Sep–14 Oct.

What’s new

30 Sep – 14 Oct 2026

3 new since 30 Sep

  1. A Reinforcement Learning Framework for Safety-Aware Haptic Shared Control in Surgical Robotics
  2. Self-Referenced Social Preferences: Cooperation without Observing Others Rewards
  3. MASkillBlender: Decentralized Whole-Body Coordination for Multi-Humanoid Loco-Manipulation via Skill Blending

Foundations

Most cited by papers here

  1. When is Mean-Field Reinforcement Learning Tractable and Relevant?2024cited by 3 here
  2. Independent Policy Mirror Descent for Markov Potential Games: Scaling to Large Number of Players2024cited by 3 here
  3. Independent Learning in Constrained Markov Potential Games2024cited by 2 here
  4. Provable Policy Gradient Methods for Average-Reward Markov Potential Games2024cited by 2 here
  5. Learning Robot Soccer from Egocentric Vision with Deep Reinforcement Learning2024cited by 2 here

Lineage

The papers this direction builds on, oldest first.

Each paper on the line cites the one before.

  1. 2024Independent Learning in Constrained Markov Potential Gamescited by 2 here
  2. 2024Independent Policy Mirror Descent for Markov Potential Games: Scaling to Large Number of Playerscited by 3 here
  3. 2025Independent Learning in Performative Markov Potential Gamescited by 2 here
21 more it builds on, not in this chain
  1. 2024Interpretable Concept Bottlenecks to Align Reinforcement Learning Agentscited by 1 here
  2. 2024Enhancing System-Level Safety in Mixed-Autonomy Platoon via Safe Reinforcement Learningcited by 1 here
  3. 2024Emergent Communication Protocol Learning for Task Offloading in Industrial Internet of Thingscited by 1 here
  4. 2024Generalization of Heterogeneous Multi-Robot Policies via Awareness and Communication of Capabilitiescited by 1 here
  5. 2024Finite-Time Analysis of On-Policy Heterogeneous Federated Reinforcement Learningcited by 1 here
  6. 2024Scalable Reinforcement Learning for Linear-Quadratic Control of Networkscited by 1 here
  7. 2024Reinforcement Learning for Versatile, Dynamic, and Robust Bipedal Locomotion Controlcited by 1 here
  8. 2024When is Mean-Field Reinforcement Learning Tractable and Relevant?cited by 3 here
  9. 2024Performative Reinforcement Learning in Gradually Shifting Environmentscited by 2 here
  10. 2024Provable Policy Gradient Methods for Average-Reward Markov Potential Gamescited by 2 here
  11. 2024Distributionally Robust Reinforcement Learning with Interactive Data Collection: Fundamental Hardness and Near-Optimal Algorithmscited by 3 here
  12. 2024A Review of Reward Functions for Reinforcement Learning in the context of Autonomous Drivingcited by 2 here
  13. 2024Learning Robot Soccer from Egocentric Vision with Deep Reinforcement Learningcited by 2 here
  14. 2024Reinforcement learningcited by 3 here
  15. 2024Gymnasium: A Standard Interface for Reinforcement Learning Environmentscited by 2 here
  16. 2024An End-to-End Reinforcement Learning Based Approach for Micro-View Order-Dispatching in Ride-Hailingcited by 2 here
  17. 2024No Regrets: Investigating and Improving Regret Approximations for Curriculum Discoverycited by 2 here
  18. 2024Online Planning for Multi-UAV Pursuit-Evasion in Unknown Environments Using Deep Reinforcement Learningcited by 2 here
  19. 2024Performative Reinforcement Learning with Linear Markov Decision Processcited by 2 here
  20. 2024Reinforcement Learning Within the Classical Robotics Stack: A Case Study in Robot Soccercited by 2 here
  21. 2025Reevaluating Policy Gradient Methods for Imperfect-Information Gamescited by 2 here

The 24 most cited of 103.

Browse

30 of 182, ranked 6–35

  1. 6Independent Learning in Performative Markov Potential Games20252
  2. 7Online Planning for Multi-UAV Pursuit-Evasion in Unknown Environments Using Deep Reinforcement Learning20242
  3. 8Mean-Field Reinforcement Learning without Synchrony20261
  4. 9Optimizing Electric Bus Charging Scheduling with Uncertainties Using Hierarchical Deep Reinforcement Learning20251
  5. 10Light Aircraft Game : Basic Implementation and training results analysis20251
  6. 11Solving Zero-Sum Convex Markov Games20251
  7. 12Achieving Logarithmic Regret in KL-Regularized Zero-Sum Markov Games20251
  8. 13Distributionally Robust Online Markov Game with Linear Function Approximation20251
  9. 14Emergent Communication Protocol Learning for Task Offloading in Industrial Internet of Things20241
  10. 15Generalization of Heterogeneous Multi-Robot Policies via Awareness and Communication of Capabilities20241
All 30
  1. 16Near-Optimal Reinforcement Learning with Self-Play under Adaptivity Constraints20241
  2. 17Refined Sample Complexity for Markov Games with Independent Linear Function Approximation20241
  3. 18Tractable Equilibrium Computation in Markov Games through Risk Aversion20241
  4. 19A Survey on Self-play Methods in Reinforcement Learning20241
  5. 20Convergence of Decentralized Actor-Critic Algorithm in General-sum Markov Games20241
  6. 21Learning Equilibria in Adversarial Team Markov Games: A Nonconvex-Hidden-Concave Min-Max Optimization Problem20241
  7. 22Learning to Cooperate with Humans using Generative Agents20241
  8. 23Sample-Efficient Policy Space Response Oracles with Joint Experience Best Response20260
  9. 24Adaptive Value Decomposition: Coordinating a Varying Number of Agents in Urban Systems20260
  10. 25AC-MASAC: An Attentive Curriculum Learning Framework for Heterogeneous UAV Swarm Coordination20260
  11. 26Convex Markov Games and Beyond: New Proof of Existence, Characterization and Learning Algorithms for Nash Equilibria20260
  12. 27Fluid-Agent Reinforcement Learning20260
  13. 28A Scalable Approach to Solving Simulation-Based Network Security Games20260
  14. 29Cooperative-Competitive Team Play of Real-World Craft Robots20260
  15. 30Heterogeneous Agent Collaborative Reinforcement Learning20260
  16. 31Principled Learning-to-Communicate with Quasi-Classical Information Structures20260
  17. 32HALO: Learning Human-Robot Collaboration via Heterogeneous-Agent Lyapunov Policy Optimization20260
  18. 33Joint Trajectory, RIS, and Computation Offloading Optimization via Decentralized Model-Based PPO in Urban Multi-UAV Mobile Edge Computing20260
  19. 34Decentralized End-to-End Multi-AAV Pursuit Using Predictive Spatio-Temporal Observation via Deep Reinforcement Learning20260
  20. 35Decentralized Task Scheduling in Distributed Systems: A Deep Reinforcement Learning Approach20260