Dec 6, 2021 · This is the first work that studies and demonstrates the effectiveness of offline pre-trained models in terms of sample efficiency and generalisability ...
Official codebase for Offline Pre-trained Multi-Agent Decision Transformer. Contains scripts to reproduce experiments. image info. Instructions.
Mar 31, 2023 · This is the first work that studies and demonstrates the effectiveness of offline pre-trained models in terms of sample efficiency and generalizability ...
Jan 28, 2022 · This work introduces the Transformer into multi-agent reinforcement learning to promote offline learning and online generalisation on downstream tasks.
People also ask
What are pre trained transformer models?
What is a decision transformer?
Offline Pre-trained Multi-agent Decision Transformer · Abstract. Offline reinforcement learning leverages previously collected offline datasets to learn optimal ...
People also search for
This paper proposes Multi-Agent Decision Transformers (MADT) for pre-training the general policy on offline datasets, capable of generalizing onto other seen/ ...
We investigate the generalization of MARL offline pre-training in the following three aspects: 1) between single agents and mul- tiple agents, 2) from offline ...
Offline reinforcement learning leverages previously-collected offline datasets to learn optimal policies with no necessity to access the real environment.
Dec 8, 2021 · "Offline Pre-trained Multi-Agent Decision Transformer (MADT): One Big Sequence Model Conquers All StarCraft II Tasks", Meng et al 2021.
This work introduces the first offline MARL dataset with diverse quality levels based on the StarCraftII environment, and proposes the novel architecture of ...