Minimizing Negative Side Effects in Cooperative Multi-Agent Systems using Distributed Coordination

Autonomous agents in real-world environments may encounter undesirable outcomes or negative side effects (NSEs) when working collaboratively alongside other agents. We frame the challenge of minimizing NSEs in a multi-agent setting as a lexicographic decentralized Markov decision process in which we assume independence of rewards and transitions with respect to the primary assigned tasks, but allowing negative side effects to create a form of dependence among the agents. We present a lexicographic Q-learning approach to mitigate the NSEs using human feedback models while maintaining near-optimality with respect to the assigned tasks—up to some given slack. Our empirical evaluation across two domains demonstrates that our collaborative approach effectively mitigates NSEs, outperforming non-collaborative methods.

Authors

• Moumita Choudhury
• Sandhya Saisubramanian Oregon State University
• Hao Zhang vivo Mobile Communication Co., Ltd
• Shlomo Zilberstein University of Massachusetts Amherst

Keywords

• AI Safety
• Negative Side Effects
• Cooperative Multi-agent Systems
• Distributed Constraint Optimization Problems