Policy Transfer across Visual and Dynamics Domain Gaps via Iterative Grounding

2021-07-01 · Grace Zhang, Linghan Zhong, Youngwoon Lee, Joseph J. Lim

The ability to transfer a policy from one environment to another is a promising avenue for efficient robot learning in realistic settings where task supervision is not available. This can allow us to take advantage of environments well suited for training, such as simulators or laboratories, to learn a policy for a real robot in a home or office. To succeed, such policy transfer must overcome both the visual domain gap (e.g. different illumination or background) and the dynamics domain gap (e.g. different robot calibration or modelling error) between source and target environments. However, prior policy transfer approaches either cannot handle a large domain gap or can only address one type of domain gap at a time. In this paper, we propose a novel policy transfer method with iterative "environment grounding", IDAPT, that alternates between (1) directly minimizing both visual and dynamics domain gaps by grounding the source environment in the target environment domains, and (2) training a policy on the grounded source environment. This iterative training progressively aligns the domains between the two environments and adapts the policy to the target environment. Once trained, the policy can be directly executed on the target environment. The empirical results on locomotion and robotic manipulation tasks demonstrate that our approach can effectively transfer a policy across visual and dynamics domain gaps with minimal supervision and interaction with the target environment. Videos and code are available at https://clvrai.com/idapt .

📄 PDF Abstract BibTeX arXiv:2107.00339

Code (1)

clvrai/idapt 공식 구현 pytorch

Transfer Value or Policy? A Value-centric Framework Towards Transferrable Continuous Reinforcement Learning

2018-09-27 · Xingchao Liu, Tongzhou Mu, Hao Su

Transferring learned knowledge from one environment to another is an important step towards practical reinforcement learning (RL). In this paper, we investigate the problem of transfer learning across environments with d…

continuous-control Continuous Control 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

BIFROST: Bridging Invariant Feature Representation for Observation-space Sim2Real Transfer

2026-07-01 · Yunfu Deng, Josiah P. Hanna arxiv

Sim2real transfer for robot policy learning suffers due to mismatch between simulation and reality. Existing methods typically address each gap in isolation through separate adaptation modules, which are composed or laye…

Domain Adaptation Visual Navigation

VAMPO: Policy Optimization for Improving Visual Dynamics in Video Action Models

2026-03-19 · Zirui Ge, Pengxiang Ding, Baohua Yin, Qishen Wang 외 arxiv

Video action models are an appealing foundation for Vision--Language--Action systems because they can learn visual dynamics from large-scale video data and transfer this knowledge to downstream robot control. Yet current…

Visual Transfer for Reinforcement Learning via Wasserstein Domain Confusion

2020-06-04 · Josh Roy, George Konidaris

We introduce Wasserstein Adversarial Proximal Policy Optimization (WAPPO), a novel algorithm for visual transfer in Reinforcement Learning that explicitly learns to align the distributions of extracted features between a…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)