Guided Deep Reinforcement Learning for Swarm Systems

Understand

In this paper, we investigate how to learn to control a group of cooperative agents with limited sensing capabilities such as robot swarms.

• The agents have only very basic sensor capabilities, yet in a group they can accomplish sophisticated tasks, such as distributed assembly or search and rescue tasks.
• Learning a policy for a group of agents is difficult due to distributed partial observability of the state.
• Here, we follow a guided approach where a critic has central access to the global state during learning, which simplifies the policy evaluation problem from a reinforcement learning point of view.