On Visual Feature Representations for Transition State Learning in Robotic Task Demonstrations
نویسندگان
چکیده
Animesh Garg* [email protected] Sanjay Krishnan* [email protected] Adithyavairavan Murali [email protected] Florian T. Pokorny [email protected] Pieter Abbeel [email protected] Trevor Darrell [email protected] Ken Goldberg [email protected] * denotes equal contribution Departments of IEOR and EECS, University of California, Berkeley Berkeley, CA 94720-1777, USA
منابع مشابه
Learning Task-Specific State Representations by Maximizing Slowness and Predictability
The success of reinforcement learning in robotic tasks is highly dependent on the state representation – a mapping from high dimensional sensory observations of the robot to states that can be used for reinforcement learning. Even though many methods have been proposed to learn state representations, it remains an important open problem. Identifying the characteristics existing methods are opti...
متن کاملEfficient Inverse Reinforcement Learning using Adaptive State-Graphs
Inverse Reinforcement Learning (IRL) provides a powerful mechanism for learning complex behaviors from demonstration by rationalizing such demonstrations. Unfortunately its applicability has been largely hindered by lack of powerful representations that can take advantage of various task affordances while still admitting scalability. Inspired by the success of sampling based approaches in class...
متن کاملLearning task goals interactively with visual demonstrations
Humans are extremely good at quickly teaching and learning new tasks through situated instructions; tasks such as learning a novel game or household chore. From studying such instructional interactions, we have observed that humans excel at communicating information through multiple modalities, including visual, linguistic, and physical ones. Rosie is a tabletop robot implemented in the Soar ar...
متن کاملLearning state representations with robotic priors
Robot learning is critically enabled by the availability of appropriate state representations. We propose a robotics-specific approach to learning such state representations. As robots accomplish tasks by interacting with the physical world, we can facilitate representation learning by considering the structure imposed by physics; this structure is reflected in the changes that occur in the wor...
متن کاملDeep Object-Centric Representations for Generalizable Robot Learning
Robotic manipulation in complex open-world scenarios requires both reliable physical manipulation skills and effective and generalizable perception. In this paper, we propose a method where general purpose pretrained visual models serve as an object-centric prior for the perception system of a learned policy. We devise an object-level attentional mechanism that can be used to determine relevant...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2016