mlsanityData to 14 Oct 2026

Influencing Towards Stable Multi-Agent Interactions

arXiv 2110.08229 ↗First posted 5 Oct 2021cs.RO cs.AI cs.LGcited by 24

Not on the map. Why?

Abstract (arXiv)

Learning in multi-agent environments is difficult due to the non-stationarity introduced by an opponent's or partner's changing behaviors. Instead of reactively adapting to the other agent's (opponent or partner) behavior, we propose an algorithm to proactively influence the other agent's strategy to stabilize -- which can restrain the non-stationarity caused by the other agent. We learn a low-dimensional latent representation of the other agent's strategy and the dynamics of how the latent strategy evolves with respect to our robot's behavior. With this learned dynamics model, we can define an unsupervised stability reward to train our robot to deliberately influence the other agent to stabilize towards a single strategy. We demonstrate the effectiveness of stabilizing in improving efficiency of maximizing the task reward in a variety of simulated environments, including autonomous driving, emergent communication, and robotic manipulation. We show qualitative results on our website: https://sites.google.com/view/stable-marl/.

Key facts. Cited by 24 papers in the map (data through 14 Oct 2026). Builds on 28 of its 52 references that are in the map. First posted on arXiv 5 Oct 2021.

Builds on

28 of 52 references.

References · 28

  1. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  2. 2013Playing Atari with Deep Reinforcement Learningcited by 3,274
  3. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,739
  4. 2016OpenAI Gymcited by 1,736
  5. 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,558
  6. 2017Curiosity-driven Exploration by Self-supervised Predictioncited by 1,194
  7. 2016The Concrete Distribution: A Continuous Relaxation of Discrete Random Variablescited by 1,148
  8. 2017Counterfactual Multi-Agent Policy Gradientscited by 751
  9. 2016Unifying Count-Based Exploration and Intrinsic Motivationcited by 639
  10. 2016Learning to Communicate with Deep Multi-Agent Reinforcement Learningcited by 575
  11. 2019Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variablescited by 389
  12. 2019On the Utility of Learning about Humans for Human-AI Coordinationcited by 349
16 more
  1. 2015Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Imagescited by 274
  2. 2017Learning with Opponent-Learning Awarenesscited by 222
  3. 2014A* Samplingcited by 151
  4. 2017Stabilising Experience Replay for Deep Multi-Agent Reinforcement Learningcited by 117
  5. 2016Opponent Modeling in Deep Reinforcement Learningcited by 97
  6. 2017A Survey of Learning in Multiagent Environments: Dealing with Non-Stationaritycited by 94
  7. 2020Learning Latent Representations to Influence Multi-Agent Interactioncited by 93
  8. 2013Hidden Parameter Markov Decision Processes: A Semiparametric Regression Approach for Discovering Latent Task Parametrizationscited by 70
  9. 2020Learning to Incentivize Other Learning Agentscited by 57
  10. 2018Learning Policy Representations in Multiagent Systemscited by 48
  11. 2019Coordinated Exploration via Intrinsic Rewards for Multi-Agent Reinforcement Learningcited by 30
  12. 2021On the Critical Role of Conventions in Adaptive Human-AI Collaborationcited by 27
  13. 2020Multi-Agent Safe Planning with Gaussian Processescited by 13
  14. 2021Emergent Prosociality in Multi-Agent Games Through Giftingcited by 12
  15. 2019Learning from My Partner's Actions: Roles in Decentralized Robot Teamscited by 10
  16. 2018Scaling simulation-to-real transfer by learning composable robot skillscited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 6; 2023: 8; 2024: 5; 2025: 3; 2026: 2.

24 papers.

Sort:

By area:

  1. 2023Stabilize to Act: Learning to Coordinate for Bimanual Manipulationcited by 39
  2. 2022Influencing Long-Term Behavior in Multiagent Reinforcement Learningcited by 18
  3. 2024A Review of the Applications of Deep Learning-Based Emergent Communicationcited by 17
  4. 2024AnyBimanual: Transferring Unimanual Policy for General Bimanual Manipulationcited by 16
  5. 2022Conditional Imitation Learning for Multi-Agent Gamescited by 13
  6. 2023Learning Vision-based Pursuit-Evasion Robot Policiescited by 11
  7. 2022RILI: Robustly Influencing Latent Intentcited by 8
  8. 2024Multi-Agent Inverse Reinforcement Learning in Real World Unstructured Pedestrian Crowdscited by 6
  9. 2022Game-Theoretical Perspectives on Active Equilibria: A Preferred Solution Concept over Nash Equilibriacited by 5
  10. 2022Learning Latent Representations to Co-Adapt to Humanscited by 5
  11. 2023iPLAN: Intent-Aware Planning in Heterogeneous Traffic via Distributed Multi-Agent Reinforcement Learningcited by 5
  12. 2023PeRP: Personalized Residual Policies For Congestion Mitigation Through Co-operative Advisory Systemscited by 4
12 more
  1. 2025Improving Human-AI Coordination through Online Adversarial Training and Generative Modelscited by 3
  2. 2023Off-Policy Evaluation for Action-Dependent Non-Stationary Environmentscited by 2
  3. 2023Learning to Influence Human Behavior with Offline Reinforcement Learningcited by 2
  4. 2023A behavioural transformer for effective collaboration between a robot and a non-stationary humancited by 2
  5. 2023Multi-Agent Strategy Explanations for Human-Robot Collaborationcited by 2
  6. 2024Learning Communication Policies for Different Follower Behaviors in a Collaborative Reference Gamecited by 1
  7. 2024Attaining Human`s Desirable Outcomes in Human-AI Interaction via Structural Causal Gamescited by 1
  8. 2025Modular Speaker Architecture: A Framework for Sustaining Responsibility and Contextual Integrity in Multi-Agent AI Communicationcited by 1
  9. 2025Topology Enhanced MARL for Multi-Agent Cooperative Decision-Making of CAVscited by 1
  10. 2026Robots Influencing Humans to Reveal their Goals during Collaboration and Competitioncited by 1
  11. 2022Asynchronous, Option-Based Multi-Agent Policy Gradient: A Conditional Reasoning Approachcited by 0
  12. 2026Model-Agnostic Lifelong LLM Safety via Externalized Attack-Defense Co-Evolutioncited by 0