Learning Action-Transferable Policy with Action Embedding

2019-09-05 · Yu Chen, Yingfeng Chen, Zhipeng Hu, Tianpei Yang, Changjie Fan, Yang Yu, Jianye Hao

Transfer learning (TL) is a promising way to improve the sample efficiency of reinforcement learning. However, how to efficiently transfer knowledge across tasks with different state-action spaces is investigated at an early stage. Most previous studies only addressed the inconsistency across different state spaces by learning a common feature space, without considering that similar actions in different action spaces of related tasks share similar semantics. In this paper, we propose a method to learning action embeddings by leveraging this idea, and a framework that learns both state embeddings and action embeddings to transfer policy across tasks with different state and action spaces. Our experimental results on various tasks show that the proposed method can not only learn informative action embeddings but accelerate policy learning.

📄 PDF Abstract BibTeX arXiv:1909.02291

Code (1)

ActionEmbedding/ActionEmbedding 공식 구현 tf

Tasks

Continuous Control Reinforcement Learning Reinforcement Learning (RL)Transfer Learning

Learning Transferable Dynamics Priors from Action to World Modeling

2026-06-28 · Ze Huang, Jiahui Zhang, Hairuo Liu, Chenxi Zhang 외 arxiv

We study action-conditioned world modeling as a scalable way to learn transferable dynamics priors for robot learning. By pretraining a model to predict how actions drive visual scene evolution, the resulting world model…

Robot Manipulation Video Generation

Translating Flow to Policy via Hindsight Online Imitation

2025-12-22 · Yitian Zheng, Zhangchen Ye, Weijun Dong, Shengjie Wang 외 arxiv

Recent advances in hierarchical robot systems leverage a high-level planner to propose task plans and a low-level policy to generate robot actions. This design allows training the planner on action-free or even non-robot…

Structure-Aware Transformer Policy for Inhomogeneous Multi-Task Reinforcement Learning

2021-09-29 · ICLR 2022 4 · Sunghoon Hong, Deunsol Yoon, Kee-Eung Kim

Modular Reinforcement Learning, where the agent is assumed to be morphologically structured as a graph, for example composed of limbs and joints, aims to learn a policy that is transferable to a structurally similar but …

Multi-Task Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)+1

HumanoidArena: Benchmarking Egocentric Hierarchical Whole-body Learning

2026-06-16 · Taowen Wang, Zikang Xie, Bin Yang, Yunheng Wang 외 arxiv

Humanoid robots promise whole-body interaction in human-centered environments, but scalable policy learning remains difficult because task-level decision-making and whole-body dynamic execution are tightly coupled. A pra…

Decision Making

Meta Dialogue Policy Learning

2020-06-03 · Yumo Xu, Chenguang Zhu, Baolin Peng, Michael Zeng

Dialog policy determines the next-step actions for agents and hence is central to a dialogue system. However, when migrated to novel domains with little data, a policy model can fail to adapt due to insufficient interact…

Meta-Learning Transfer Learning