Next
Livestream will start soon!
Livestream has already ended.
Presentation has not been recorded yet!
  • title: Controllability-Aware Unsupervised Skill Discovery
      0:00 / 0:00
      • Report Issue
      • Settings
      • Playlists
      • Bookmarks
      • Subtitles Off
      • Playback rate
      • Quality
      • Settings
      • Debug information
      • Server sl-yoda-v2-stream-001-alpha.b-cdn.net
      • Subtitles size Medium
      • Bookmarks
      • Server
      • sl-yoda-v2-stream-001-alpha.b-cdn.net
      • sl-yoda-v2-stream-001-beta.b-cdn.net
      • 1824830694.rsc.cdn77.org
      • 1979322955.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
            Controllability-Aware Unsupervised Skill Discovery
            • Settings
            • Sync diff
            • Quality
            • Settings
            • Server
            • Quality
            • Server

            Controllability-Aware Unsupervised Skill Discovery

            Jul 24, 2023

            Speakers

            SP

            Seohong Park

            Speaker · 0 followers

            KL

            Kimin Lee

            Speaker · 0 followers

            YL

            Youngwoon Lee

            Speaker · 0 followers

            About

            One of the key capabilities of intelligent agents is the ability to discover useful skills without external supervision. However, the current unsupervised skill discovery methods are often limited to acquiring simple, easy-to-learn skills due to the lack of incentives to discover more complex, challenging behaviors. We introduce a novel unsupervised skill discovery method, **Controllability-aware Skill Discovery** (**CSD**), which actively seeks complex, hard-to-control skills without supervisi…

            Organizer

            I2
            I2

            ICML 2023

            Account · 657 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

            SinDDM: A Single Image Denoising Diffusion Model
            05:09

            SinDDM: A Single Image Denoising Diffusion Model

            Vladimir Kulikov, …

            I2
            I2
            ICML 2023 2 years ago

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

            Reality-Centric AI
            34:03

            Reality-Centric AI

            Mihaela van der Schaar

            I2
            I2
            ICML 2023 2 years ago

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

            Quantile Credit Assignment
            10:51

            Quantile Credit Assignment

            Thomas Mesnard, …

            I2
            I2
            ICML 2023 2 years ago

            Total of 1 viewers voted for saving the presentation to eternal vault which is 0.1%

            Can We Scale Transformers to Predict Parameters of Diverse ImageNet Models?
            05:05

            Can We Scale Transformers to Predict Parameters of Diverse ImageNet Models?

            Boris Knyazev, …

            I2
            I2
            ICML 2023 2 years ago

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

            Enforcing Right to Explanation: Technical Challenges, Solutions, and Opportunities
            29:50

            Enforcing Right to Explanation: Technical Challenges, Solutions, and Opportunities

            Hima Lakkaraju

            I2
            I2
            ICML 2023 2 years ago

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

            MG-GNN: Multigrid Graph Neural Networks for Learning Multilevel Domain Decomposition Methods
            04:45

            MG-GNN: Multigrid Graph Neural Networks for Learning Multilevel Domain Decomposition Methods

            Ali Taghibakhshi, …

            I2
            I2
            ICML 2023 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 ICML 2023