When Does Communication Learning Need Hierarchical Multi-Agent Deep Reinforcement Learning
By Marie Ossenkopf, Mackenzie Jorgensen, Kurt Geihs. 2019
6 citations recorded by the source corpus.
Abstract Multi-agent systems need to communicate to coordinate a shared task. We show that a recurrent neural network (RNN) can learn a communication protocol for coordination, even if the actions to coordinate are performed steps after the communication phase. We show that a separation of tasks with different temporal scale is necessary for successful learning. We contribute a hierarchical deep reinforcement learning model for multi-agent systems that separates the communication and coordination task from the action picking through a hierarchical policy. We further on show, that a separation of concerns in communication is beneficial but not necessary. As a testbed, we propose the Dungeon Lever Game and we extend the Differentiable Inter-Agent Learning (DIAL) framework. We present and compare results from different model variations on the Dungeon Lever Game.
Subfields: Artificial Intelligence, Sociology and Political Science
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Chongjie Zhang
- Tonghan Wang
- Bei Peng
- Shimon Whiteson
- Anuj Mahajan
- Tarun Gupta
- Christian Schröder de Witt
- J. Urgen Schmidhuber
In Sociology and Political Science
Citations in the corpus
- RODE: Learning Roles to Decompose Multi-Agent Tasks (2020, background): “In multi-agent settings, many challenges, such as efficient communication (Ossenkopf et al., 2019) and labor division (Wang et al., 2020c) in large systems, necessitate hierarchical learning along the second dimension – over agents (Zhang et al., 2010).”