AI Bibliography
AI Bibliography |
|
 |
 |
 |
|
Inala, J. P., Yang, Y., Paulos, J., Pu, Y., Bastani, O., & Kumar, V., et al.. (2020). Neurosymbolic transformers for multi-agent communication. Advances in Neural Information Processing Systems, 33. |
| Resource type: Journal Article BibTeX citation key: Inala2020 View all bibliographic details  |
Categories: Artificial Intelligence, Biological Science, Cognitive Science, Complexity Science, Computer Science, Data Sciences, Decision Theory, General, Mathematics Subcategories: Autonomous systems, Big data, Decision making, Edge AI, Internet of things, Machine learning, Machine recognition, Markov models, Neural nets, Neurosymbolic, Systems theory Creators: Bastani, Inala, Kumar, Paulos, Pu, Rinard, Solar-Lezama, Yang Publisher: Collection: Advances in Neural Information Processing Systems |
| Attachments |
| Abstract |
|
We study the problem of inferring communication structures that can solve cooperative multi-agent planning problems while minimizing the amount of communication. We quantify the amount of communication as the maximum degree of the communication graph; this metric captures settings where agents have limited bandwidth. Minimizing communication is challenging due to the combinatorial nature of both the decision space and the objective; for instance, we cannot solve this problem by training neural networks using gradient descent. We propose a novel algorithm that synthesizes a control policy that combines a programmatic communication policy used to generate the communication graph with a transformer policy network used to choose actions. Our algorithm first trains the transformer policy, which implicitly generates a "soft" communication graph; then, it synthesizes a programmatic communication policy that "hardens" this graph, forming a neurosymbolic transformer. Our experiments demonstrate how our approach can synthesize policies that generate low-degree communication graphs while maintaining near-optimal performance.
|