Next
Livestream will start soon!
Livestream has already ended.
Presentation has not been recorded yet!
  • title: Visual Backtracking Teleoperation: A Data Collection Protocol for Offline Image-Based Reinforcement Learning
      0:00 / 0:00
      • Report Issue
      • Settings
      • Playlists
      • Bookmarks
      • Subtitles Off
      • Playback rate
      • Quality
      • Settings
      • Debug information
      • Server sl-yoda-v2-stream-009-alpha.b-cdn.net
      • Subtitles size Medium
      • Bookmarks
      • Server
      • sl-yoda-v2-stream-009-alpha.b-cdn.net
      • sl-yoda-v2-stream-009-beta.b-cdn.net
      • 1766500541.rsc.cdn77.org
      • 1441886916.rsc.cdn77.org
      • Subtitles
      • Off
      • English
      • Playback rate
      • Quality
      • Subtitles size
      • Large
      • Medium
      • Small
      • Mode
      • Video Slideshow
      • Audio Slideshow
      • Slideshow
      • Video
      My playlists
        Bookmarks
          00:00:00
            Visual Backtracking Teleoperation: A Data Collection Protocol for Offline Image-Based Reinforcement Learning
            • Settings
            • Sync diff
            • Quality
            • Settings
            • Server
            • Quality
            • Server

            Visual Backtracking Teleoperation: A Data Collection Protocol for Offline Image-Based Reinforcement Learning

            Dec 2, 2022

            Speakers

            DB

            David Brandfonbrener

            Speaker · 0 followers

            ST

            Stephen Tu

            Speaker · 0 followers

            AS

            Avi Singh

            Speaker · 0 followers

            About

            We consider how to most efficiently leverage teleoperator time to collect data for learning robust image-based value functions and policies for sparse reward robotic tasks. To accomplish this goal, we modify the process of data collection to include more than just successful demonstrations of the desired task. Instead we develop a novel protocol that we call Visual Backtracking Teleoperation (VBT), which deliberately collects a dataset of visually similar failures, recoveries, and successes. VBT…

            Organizer

            N2
            N2

            NeurIPS 2022

            Account · 952 followers

            Like the format? Trust SlidesLive to capture your next event!

            Professional recording and live streaming, delivered globally.

            Sharing

            Recommended Videos

            Presentations on similar topic, category or speaker

            Defining and Characterizing Reward Hacking
            05:03

            Defining and Characterizing Reward Hacking

            Joar Skalse, …

            N2
            N2
            NeurIPS 2022 2 years ago

            Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%

            Lightweight Protein Engineering with Equivariant Graph Representation Learning
            02:08

            Lightweight Protein Engineering with Equivariant Graph Representation Learning

            Bingxin Zhou, …

            N2
            N2
            NeurIPS 2022 2 years ago

            Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%

            Featured Papers Panels 4C
            1:15:12

            Featured Papers Panels 4C

            N2
            N2
            NeurIPS 2022 2 years ago

            Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%

            Distributionally Robust Weighted k-Nearest Neighbors
            06:34

            Distributionally Robust Weighted k-Nearest Neighbors

            Shixiang Zhu, …

            N2
            N2
            NeurIPS 2022 2 years ago

            Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%

            The IHME COVID-19 Forecasting model
            39:34

            The IHME COVID-19 Forecasting model

            Bobby Reiner

            N2
            N2
            NeurIPS 2022 2 years ago

            Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%

            On the Unreasonable Effectiveness of Federated Averaging with Heterogenous Data
            15:40

            On the Unreasonable Effectiveness of Federated Averaging with Heterogenous Data

            Jianyu Wang, …

            N2
            N2
            NeurIPS 2022 2 years ago

            Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%

            Interested in talks like this? Follow NeurIPS 2022