We present RoM-Q 1, a new Q-learning-like algorithm for finding policies robust to attacks in multi-agent systems (MAS). We consider a novel type of attack, where a team of adversaries, aware of the optimal multi-agent Q-value function, performs a worst-case selection of both the agents to attack and the actions to perform. Our motivation lies in real-world MAS where vulnerabilities of particular agents emerge due to their characteristics and robust policies need to be learned without requiring the simulation of attacks during training. In our simulations, where we train policies using RoMQ, Q-learning and minimax-Q and derive corresponding adversarial attacks, we observe that policies learned using RoM-Q are more robust, as they accrue the...
Tackling overestimation in Q-learning is an important problem that has been extensively studied in s...
Although well understood in the single-agent framework, the use of traditional reinforcement learnin...
Various types of Multi-Agent Reinforcement Learning (MARL) methods have been developed, assuming tha...
Many state-of-the-art cooperative multi-agent reinforcement learning (MARL) approaches, such as MADD...
In this study, we explore the robustness of cooperative multi-agent reinforcement learning (c-MARL) ...
Communication is important in many multi-agent reinforcement learning (MARL) problems for agents to ...
International audienceThe article focuses on decentralized reinforcement learning (RL) in cooperativ...
peer reviewedThis paper introduces four new algorithms that can be used for tackling multi-agent rei...
We describe a generalized Q-learning type algorithm for reinforcement learning in competitive multi-...
On-line learning methods have been applied successfully in multi-agent systems to achieve coordinati...
Cooperative multi-agent reinforcement learning (cMARL) has many real applications, but the policy tr...
Multiagent decision-making is a ubiquitous problem with many real-world applications, such as autono...
We present an approach to reduce the communication required between agents in a Multi-Agent learning...
In offline multi-agent reinforcement learning (MARL), agents estimate policies from a given dataset....
A multi-agent policy iteration learning algorithm is proposed in this work. The Exponential Moving A...
Tackling overestimation in Q-learning is an important problem that has been extensively studied in s...
Although well understood in the single-agent framework, the use of traditional reinforcement learnin...
Various types of Multi-Agent Reinforcement Learning (MARL) methods have been developed, assuming tha...
Many state-of-the-art cooperative multi-agent reinforcement learning (MARL) approaches, such as MADD...
In this study, we explore the robustness of cooperative multi-agent reinforcement learning (c-MARL) ...
Communication is important in many multi-agent reinforcement learning (MARL) problems for agents to ...
International audienceThe article focuses on decentralized reinforcement learning (RL) in cooperativ...
peer reviewedThis paper introduces four new algorithms that can be used for tackling multi-agent rei...
We describe a generalized Q-learning type algorithm for reinforcement learning in competitive multi-...
On-line learning methods have been applied successfully in multi-agent systems to achieve coordinati...
Cooperative multi-agent reinforcement learning (cMARL) has many real applications, but the policy tr...
Multiagent decision-making is a ubiquitous problem with many real-world applications, such as autono...
We present an approach to reduce the communication required between agents in a Multi-Agent learning...
In offline multi-agent reinforcement learning (MARL), agents estimate policies from a given dataset....
A multi-agent policy iteration learning algorithm is proposed in this work. The Exponential Moving A...
Tackling overestimation in Q-learning is an important problem that has been extensively studied in s...
Although well understood in the single-agent framework, the use of traditional reinforcement learnin...
Various types of Multi-Agent Reinforcement Learning (MARL) methods have been developed, assuming tha...