MAMPS: Safe Multi-Agent Reinforcement Learning via Model Predictive Shielding

Understand

Reinforcement learning is a promising approach to learning control policies for performing complex multi-agent robotics tasks.

• However, a policy learned in simulation often fails to guarantee even simple safety properties such as obstacle avoidance.
• To ensure safety, we propose multi-agent model predictive shielding (MAMPS), an algorithm that provably guarantees safety for an arbitrary learned policy.
• In particular, it operates by using the learned policy as often as possible, but instead uses a backup policy in cases where it cannot guarantee the safety of the learned policy.