Ad Hoc Teamwork in the Presence of Adversaries
Not on the map. Why?
Abstract (arXiv)
Advances in ad hoc teamwork have the potential to create agents that collaborate robustly in real-world applications. Agents deployed in the real world, however, are vulnerable to adversaries with the intent to subvert them. There has been little research in ad hoc teamwork that assumes the presence of adversaries. We explain the importance of extending ad hoc teamwork to include the presence of adversaries and clarify why this problem is difficult. We then propose some directions for new research opportunities in ad hoc teamwork that leads to more robust multi-agent cyber-physical infrastructure systems.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 23 of its 36 references that are in the map. First posted on arXiv 9 Aug 2022.
Builds on
23 of 36 references.
References · 23
- 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,519
- 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
- 2018QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learningcited by 697
- 2020Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learningcited by 475
- 2017Robust Adversarial Reinforcement Learningcited by 439
- 2017Adversarial Attacks on Neural Network Policiescited by 314
- 2019Adversarial Policies: Attacking Deep Reinforcement Learningcited by 209
- 2020Open Problems in Cooperative AIcited by 167
- 2021Collaborating with Humans without Human Datacited by 139
- 2021Off-Belief Learningcited by 72
- 2020Stealthy and Efficient Adversarial Attacks against Deep Reinforcement Learningcited by 62
- 2019Risk Averse Robust Adversarial Reinforcement Learningcited by 54
11 more
- 2021Scientific multi-agent reinforcement learning for wall-models of turbulent flowscited by 52
- 2021Multi-Agent Reinforcement Learning for Active Voltage Control on Power Distribution Networkscited by 52
- 2021Adversarial Attacks On Multi-Agent Communicationcited by 48
- 2020On the Robustness of Cooperative Multi-Agent Reinforcement Learningcited by 39
- 2020Towards Open Ad Hoc Teamwork Using Graph-based Policy Learningcited by 37
- 2021A New Formalism, Method and Open Issues for Zero-Shot Coordinationcited by 31
- 2021Expected Value of Communication for Planning in Ad Hoc Teamworkcited by 19
- 2021Adversarial attacks in consensus-based multi-agent reinforcement learningcited by 17
- 2021PowerGridworld: A Framework for Multi-Agent Reinforcement Learning in Power Systemscited by 15
- 2021GridLearn: Multiagent Reinforcement Learning for Grid-Aware Building Energy Managementcited by 12
- 2021Reward-Free Attacks in Multi-Agent Reinforcement Learningcited by 3
Built on by
Citing papers per year: 2025: 1.
1 paper.