Efficient Multi-Task and Transfer Reinforcement Learning with Parameter-Compositional Framework

2023-06-02 · Lingfeng Sun, Haichao Zhang, Wei Xu, Masayoshi Tomizuka

In this work, we investigate the potential of improving multi-task training and also leveraging it for transferring in the reinforcement learning setting. We identify several challenges towards this goal and propose a transferring approach with a parameter-compositional formulation. We investigate ways to improve the training of multi-task reinforcement learning which serves as the foundation for transferring. Then we conduct a number of transferring experiments on various manipulation tasks. Experimental results demonstrate that the proposed approach can have improved performance in the multi-task training stage, and further show effective transferring in terms of both sample efficiency and performance.

📄 PDF Abstract BibTeX arXiv:2306.01839

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learning Reinforcement LearningTransfer Reinforcement Learning

Compositional Transfer in Hierarchical Reinforcement Learning

2019-06-26 · Markus Wulfmeier, Abbas Abdolmaleki, Roland Hafner, Jost Tobias Springenberg 외

The successful application of general reinforcement learning algorithms to real-world robotics applications is often limited by their high data requirements. We introduce Regularized Hierarchical Policy Optimization (RHP…

General Reinforcement Learning Hierarchical Reinforcement Learning reinforcement-learning Reinforcement Learning+3

Zero-Shot Policy Transfer with Disentangled Task Representation of Meta-Reinforcement Learning

2022-10-01 · Zheng Wu, Yichen Xie, Wenzhao Lian, Changhao Wang 외

Humans are capable of abstracting various tasks as different combinations of multiple attributes. This perspective of compositionality is vital for human rapid learning and adaption since previous experiences from relate…

Disentanglement Meta Reinforcement Learning reinforcement-learning Reinforcement Learning (RL)

PaCo: Parameter-Compositional Multi-Task Reinforcement Learning

2022-10-21 · Lingfeng Sun, Haichao Zhang, Wei Xu, Masayoshi Tomizuka

The purpose of multi-task reinforcement learning (MTRL) is to train a single policy that can be applied to a set of different tasks. Sharing parameters allows us to take advantage of the similarities among tasks. However…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Adapter-TST: A Parameter Efficient Method for Multiple-Attribute Text Style Transfer

2023-05-10 · Zhiqiang Hu, Roy Ka-Wei Lee, Nancy F. Chen

Adapting a large language model for multiple-attribute text style transfer via fine-tuning can be challenging due to the significant amount of computational resources and labeled data required for the specific task. In t…

Attribute Language Modeling Language Modelling Large Language Model+3

Semantically Structured Mixture-of-Experts for Compositional Robotic Manipulation

2026-05-22 · Chengyu Deng, Guanqi Chen, Yizhou Chen, Zejia Liu 외 arxiv

Diffusion-based policies have established a new standard for precise robotic manipulation but face a critical scalability bottleneck: high-performance models are computationally expensive, while lightweight alternatives …

parameter-efficient fine-tuning