Abstract
Models based on the Transformer architecture have seen widespread application across fields such as natural language processing (NLP), computer vision, and robotics, with large language models (LLMs) like ChatGPT revolutionizing machine understanding of human language and demonstrating impressive memory and reproduction capabilities. Traditional machine learning algorithms struggle with catastrophic forgetting, which is detrimental to the diverse and generalized abilities required for robotic deployment. This paper investigates the Receptance Weighted Key Value (RWKV) framework, known for its advanced capabilities in efficient and effective sequence modeling, integration with the decision transformer (DT), and experience replay architectures. It focuses on potential performance enhancements in sequence decision-making and lifelong robotic learning tasks. We introduce the Decision-RWKV (DRWKV) model and conduct extensive experiments using the D4RL database within the OpenAI Gym environment and on the D’Claw platform to assess the DRWKV model's performance in single-task tests and lifelong learning scenarios, showcasing its ability to handle multiple subtasks efficiently. The code for all algorithms, training, and image rendering in this study is open-sourced at https://github.com/ancorasir/DecisionRWKV.
Links
BibTeX (Download)
@online{Dong2024OptimizingRobotic,
title = {Optimizing Robotic Manipulation with Decision-RWKV: A Recurrent Sequence Modeling Approach for Lifelong Learning},
author = {Yujian Dong and Tianyu Wu and Chaoyang Song},
doi = {10.48550/arXiv.2407.16306},
year = {2024},
date = {2024-06-30},
abstract = {Models based on the Transformer architecture have seen widespread application across fields such as natural language processing (NLP), computer vision, and robotics, with large language models (LLMs) like ChatGPT revolutionizing machine understanding of human language and demonstrating impressive memory and reproduction capabilities. Traditional machine learning algorithms struggle with catastrophic forgetting, which is detrimental to the diverse and generalized abilities required for robotic deployment. This paper investigates the Receptance Weighted Key Value (RWKV) framework, known for its advanced capabilities in efficient and effective sequence modeling, integration with the decision transformer (DT), and experience replay architectures. It focuses on potential performance enhancements in sequence decision-making and lifelong robotic learning tasks. We introduce the Decision-RWKV (DRWKV) model and conduct extensive experiments using the D4RL database within the OpenAI Gym environment and on the D’Claw platform to assess the DRWKV model's performance in single-task tests and lifelong learning scenarios, showcasing its ability to handle multiple subtasks efficiently. The code for all algorithms, training, and image rendering in this study is open-sourced at https://github.com/ancorasir/DecisionRWKV. },
note = {Submitted to the Special Issue on Large Language Models In Design And Manufacturing in the Journal of Computing and Information Science in Engineering},
keywords = {Corresponding Author, Under Review},
pubstate = {forthcoming},
tppubtype = {online}
}
