Learning to Communicate: A Machine Learning Framework for Heterogeneous Multi-Agent Robotic Systems
| Autor: | Hyung-Jin Yoon, Aditya Gahlawat, Donghwan Lee, Huaiyu Chen, Naira Hovakimyan, Heling Zhang, Kehan Long |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2018 |
| Předmět: |
FOS: Computer and information sciences
0209 industrial biotechnology Computer science business.industry Computer Science - Artificial Intelligence Resource constraints 02 engineering and technology Space (commercial competition) 3d simulation Machine learning computer.software_genre Computer Science - Robotics Artificial Intelligence (cs.AI) 020901 industrial engineering & automation Robotic systems Action (philosophy) Encoding (memory) 0202 electrical engineering electronic engineering information engineering Reinforcement learning 020201 artificial intelligence & image processing Artificial intelligence Actuator business Robotics (cs.RO) computer |
| Popis: | 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. AIAA SciTech 2019 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|