Know Thyself: Transferable Visual Control Policies Through Robot-Awareness
Training visual control policies from scratch on a new robot typically requires generating large amounts of robot-specific data. How might we leverage data previously collected on another robot to reduce or even completely remove this need for robot-specific data? We propose a "robot-aware control" paradigm that achieves this by exploiting readily available knowledge about the robot. We then instantiate this in a robot-aware model-based RL policy by training modular dynamics models that couple a transferable, robot-aware world dynamics module with a robot-specific, potentially analytical, robot dynamics module. This also enables us to set up visual planning costs that separately consider the robot agent and the world. Our experiments on tabletop manipulation tasks with simulated and real robots demonstrate that these plug-in improvements dramatically boost the transferability of visual model-based RL policies, even permitting zero-shot transfer of visual manipulation skills onto new robots. Project website: https://www.seas.upenn.edu/~hued/rac
Code (1)
Tasks
Model-based Reinforcement LearningTransfer LearningVideo PredictionSimilar Papers 제목 키워드 기반
KnowThyself: An Agentic Assistant for LLM Interpretability
We develop KnowThyself, an agentic assistant that advances large language model (LLM) interpretability. Existing tools provide useful insights but remain fragmented and code-intensive. KnowThyself consolidates these capa…
Transferable Visual Control Policies Through Robot-Awareness
Training visual control policies from scratch on a new robot typically requires generating large amounts of robot-specific data. Could we leverage data previously collected on another robot to reduce or even completely r…
Learning Transferable Policies for Monocular Reactive MAV Control
The ability to transfer knowledge gained in previous tasks into new contexts is one of the most important mechanisms of human learning. Despite this, adapting autonomous behavior to be reused in partially similar setting…
VideoWorld 2: Learning Transferable Knowledge from Real-world Videos
Learning transferable knowledge from unlabeled video data and applying it in new environments is a fundamental capability of intelligent agents. This work presents VideoWorld 2, which extends VideoWorld and offers the fi…
Video GenerationSupervise Thyself: Examining Self-Supervised Representations in Interactive Environments
Self-supervised methods, wherein an agent learns representations solely by observing the results of its actions, become crucial in environments which do not provide a dense reward signal or have labels. In most cases, su…
Imitation Learning