Learning to Communicate: A Machine Learning Framework for Heterogeneous Multi-Agent Robotic Systems
This work addresses communication challenges in multi-agent robotics, but it appears incremental as it extends existing reinforcement learning frameworks to include communication actions without major breakthroughs.
The authors tackled the problem of enabling heterogeneous multi-agent robotic systems to learn both optimal policies and efficient encodings of high-dimensional visual observations for communication under resource constraints, demonstrating feasibility in a 3D simulation with two collaborating agents.
We present a machine learning framework for multi-agent systems to learn both the optimal policy for maximizing the rewards and the encoding of the high dimensional visual observation. The encoding is useful for sharing local visual observations with other agents under communication resource constraints. The actor-encoder encodes the raw images and chooses an action based on local observations and messages sent by the other agents. The machine learning agent generates not only an actuator command to the physical device, but also a communication message to the other agents. We formulate a reinforcement learning problem, which extends the action space to consider the communication action as well. The feasibility of the reinforcement learning framework is demonstrated using a 3D simulation environment with two collaborating agents. The environment provides realistic visual observations to be used and shared between the two agents.