Attention-based Fault-tolerant Approach For Multi-agent Reinforcement Learning Systems

Abstract

The aim of multi-agent reinforcement learning systems is to provide interacting agents with the ability to collaboratively learn and adapt to the behavior of other agents. In many real-world applications, the agents can only acquire a partial view of the world. However, in realistic settings, one or more agents that show arbitrarily faulty or malicious behavior may suffice to let the current coordination mechanisms fail. In this paper, we study a practical scenario considering the security issues in the presence of agents with arbitrarily faulty or malicious behavior. Under these circumstances, learning an optimal policy becomes particularly challenging, even in the unrealistic case that an agent's policy can be made conditional upon all other agents' observations. To overcome these difficulties, we present an Attention-based Fault-Tolerant (FT-Attn) algorithm which selects correct and relevant information for each agent at every time-step. The multi-head attention mechanism enables th

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keygeng2019attention

Related papers

• Fault Tolerant Multi-agent Learning With Adversarial Budget Constraints (2025)0.00
• Trust-based Consensus In Multi-agent Reinforcement Learning Systems (2022)0.00
• Actor-attention-critic For Multi-agent Reinforcement Learning (2018)0.00
• Sa-matd3:self-attention-based Multi-agent Continuous Control Method In Cooperative Environments (2021)11.76
• DSDF: An Approach To Handle Stochastic Agents In Collaborative Multi-agent Reinforcement Learning (2021)0.00
• Multi-task Federated Reinforcement Learning With Adversaries (2021)0.00
• Attention Actor-critic Algorithm For Multi-agent Constrained Co-operative Reinforcement Learning (2021)0.00
• Coach-assisted Multi-agent Reinforcement Learning Framework For Unexpected Crashed Agents (2022)0.00