深層強化学習のバックボーンとしてのTransformer in Transformer
Transformer in Transformer as Backbone for Deep Reinforcement Learning
深層強化学習向けに、単一観測を処理する内側Transformerと観測履歴を処理する外側Transformerを組み合わせた純粋なTransformerベースのバックボーンTITを提案し、オンライン・オフライン両設定で良好な性能を示した。
著者: Hangyu Mao, Rui Zhao, Hao Chen, Jianye Hao, Yiqun Chen, Dong Li, Junge Zhang, Zhen Xiao
分類: cs.LG, cs.AI, cs.RO
原文アブストラクト
Designing better deep networks and better reinforcement learning (RL) algorithms are both important for deep RL. This work focuses on the former. Previous methods build the network with several modules like CNN, LSTM and Attention. Recent methods combine the Transformer with these modules for better performance. However, it requires tedious optimization skills to train a network composed of mixed modules, making these methods inconvenient to be used in practice. In this paper, we propose to design \emph{pure Transformer-based networks} for deep RL, aiming at providing off-the-shelf backbones for both the online and offline settings. Specifically, the Transformer in Transformer (TIT) backbone is proposed, which cascades two Transformers in a very natural way: the inner one is used to process a single observation, while the outer one is responsible for processing the observation history; combining both is expected to extract spatial-temporal representations for good decision-making. Experiments show that TIT can achieve satisfactory performance in different settings consistently.
