Q-Transformer: Scalable Offline Reinforcement Learning via Autoregressive Q-FunctionsDownload PDF

Published: 30 Aug 2023, Last Modified: 17 Oct 2023CoRL 2023 PosterReaders: Everyone
Keywords: Reinforcement Learning, Offline RL, Transformers, Q-Learning, Robotic Manipulation
Abstract: In this work, we present a scalable reinforcement learning method for training multi-task policies from large offline datasets that can leverage both human demonstrations and autonomously collected data. Our method uses a Transformer to provide a scalable representation for Q-functions trained via offline temporal difference backups. We therefore refer to the method as Q-Transformer. By discretizing each action dimension and representing the Q-value of each action dimension as separate tokens, we can apply effective high-capacity sequence modeling techniques for Q-learning. We present several design decisions that enable good performance with offline RL training, and show that Q-Transformer outperforms prior offline RL algorithms and imitation learning techniques on a large diverse real-world robotic manipulation task suite.
Student First Author: no
Supplementary Material: zip
Instructions: I have read the instructions for authors (https://corl2023.org/instructions-for-authors/)
Website: https://qtransformer.github.io
Publication Agreement: pdf
Poster Spotlight Video: mp4
23 Replies