Next
Livestream will start soon!
Livestream has already ended.
Presentation has not been recorded yet!
  • title: Characterising the Robustness of Reinforcement Learning for Continuous Control using Disturbance Injection
      0:00 / 0:00
      • Report Issue
      • Settings
      • Playlists
      • Bookmarks
      • Subtitles Off
      • Playback rate
      • Quality
      • Settings
      • Debug information
      • Server sl-yoda-v2-stream-004-alpha.b-cdn.net
      • Subtitles size Medium
      • Bookmarks
      • Server
      • sl-yoda-v2-stream-004-alpha.b-cdn.net
      • sl-yoda-v2-stream-004-beta.b-cdn.net
      • 1685195716.rsc.cdn77.org
      • 1239898752.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
            Characterising the Robustness of Reinforcement Learning for Continuous Control using Disturbance Injection
            • Settings
            • Sync diff
            • Quality
            • Settings
            • Server
            • Quality
            • Server

            Characterising the Robustness of Reinforcement Learning for Continuous Control using Disturbance Injection

            Dec 2, 2022

            Speakers

            CG

            Catherine Glossop

            Speaker · 0 followers

            JP

            Jacopo Panerati

            Speaker · 0 followers

            AK

            Amrit Krishnan

            Speaker · 0 followers

            About

            In this study, we leverage the deliberate and systematic fault-injection capabilities of an open-source benchmark suite to perform a series of experiments on state-of-the-art deep and robust reinforcement learning algorithms.We aim to benchmark robustness in the context of continuous action spaces—crucial for deployment in robot control.We find that robustness is more prominent for action disturbances than it is for disturbances to observations and dynamics. We also observe that state-of-the-art…

            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

            Characterising the Robustness of Reinforcement Learning for Continuous Control using Disturbance Injection
            05:55

            Characterising the Robustness of Reinforcement Learning for Continuous Control using Disturbance Injection

            Catherine Glossop, …

            N2
            N2
            NeurIPS 2022 2 years ago

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

            Recurent Convolutional Neural Networks Learn Succinct Learning Algorithms
            03:24

            Recurent Convolutional Neural Networks Learn Succinct Learning Algorithms

            Surbhi Goel, …

            N2
            N2
            NeurIPS 2022 2 years ago

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

            A2: Efficient Automated Attacker for Boosting Adversarial Training
            01:02

            A2: Efficient Automated Attacker for Boosting Adversarial Training

            Zhuoer Xu, …

            N2
            N2
            NeurIPS 2022 2 years ago

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

            In Defense of the Unitary Scalarization for Deep Multi-Task Learning
            04:42

            In Defense of the Unitary Scalarization for Deep Multi-Task Learning

            Vitaly Kurin, …

            N2
            N2
            NeurIPS 2022 2 years ago

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

            Unsupervised Skill Discovery via Recurrent Skill Training
            04:54

            Unsupervised Skill Discovery via Recurrent Skill Training

            Zheyuan Jiang, …

            N2
            N2
            NeurIPS 2022 2 years ago

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

            Take 5: Interpretable Image Classification with a Handful of Features
            08:15

            Take 5: Interpretable Image Classification with a Handful of Features

            Thomas Norrenbrock, …

            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