Core Concepts
Efficiently solving temporally dependent multi-agent problems using transformers.
Stats
State-of-the-art solutions follow centralized training with decentralized execution paradigm to handle scalability concerns.
Transformers proposed to efficiently solve temporally dependent multi-agent problems with centralized approach.
Quotes
"In this paper, we propose time-dependent multi-agent transformers which can solve the temporally dependent multi-agent problem efficiently."
"We highlight the efficacy of this method on two problems and use tools from statistics to verify the probability that the trajectories generated under the policy satisfy the task."