PDiT: Interleaving Perception and Decision-making Transformers for Deep Reinforcement Learning

Autor:	Mao, Hangyu, Zhao, Rui, Li, Ziyue, Xu, Zhiwei, Chen, Hao, Chen, Yiqun, Zhang, Bin, Xiao, Zhen, Zhang, Junge, Yin, Jiangjin
Rok vydání:	2023
Předmět:	Computer Science - Machine Learning Computer Science - Artificial Intelligence Computer Science - Robotics Electrical Engineering and Systems Science - Systems and Control
Druh dokumentu:	Working Paper
Popis:	Designing better deep networks and better reinforcement learning (RL) algorithms are both important for deep RL. This work studies the former. Specifically, the Perception and Decision-making Interleaving Transformer (PDiT) network is proposed, which cascades two Transformers in a very natural way: the perceiving one focuses on \emph{the environmental perception} by processing the observation at the patch level, whereas the deciding one pays attention to \emph{the decision-making} by conditioning on the history of the desired returns, the perceiver's outputs, and the actions. Such a network design is generally applicable to a lot of deep RL settings, e.g., both the online and offline RL algorithms under environments with either image observations, proprioception observations, or hybrid image-language observations. Extensive experiments show that PDiT can not only achieve superior performance than strong baselines in different settings but also extract explainable feature representations. Our code is available at \url{https://github.com/maohangyu/PDiT}. Comment: Proc. of the 23rd International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2024, full paper with oral presentation). Cover our preliminary study: arXiv:2212.14538
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2312.15863 Zobrazit plný text záznamu View this record from Arxiv