MAMPS: Safe Multi-Agent Reinforcement Learning via Model Predictive Shielding
This addresses safety concerns for multi-agent robotics tasks, but it is incremental as it builds on existing shielding methods.
The paper tackles the problem of ensuring safety in multi-agent reinforcement learning policies by proposing MAMPS, which guarantees safety by using a backup policy when needed, and demonstrates good performance in a simulation environment.
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. Using a multi-agent simulation environment, we show how MAMPS can achieve good performance while ensuring safety.