Next
Livestream will start soon!
Livestream has already ended.
Presentation has not been recorded yet!
  • title: Recurrent Model-Free RL Can Be a Strong Baseline for Many POMDPs
      0:00 / 0:00
      • Report Issue
      • Settings
      • Playlists
      • Bookmarks
      • Subtitles Off
      • Playback rate
      • Quality
      • Settings
      • Debug information
      • Server sl-yoda-v2-stream-006-alpha.b-cdn.net
      • Subtitles size Medium
      • Bookmarks
      • Server
      • sl-yoda-v2-stream-006-alpha.b-cdn.net
      • sl-yoda-v2-stream-006-beta.b-cdn.net
      • 1549480416.rsc.cdn77.org
      • 1102696603.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
            Recurrent Model-Free RL Can Be a Strong Baseline for Many POMDPs
            • Settings
            • Sync diff
            • Quality
            • Settings
            • Server
            • Quality
            • Server

            Recurrent Model-Free RL Can Be a Strong Baseline for Many POMDPs

            Jul 19, 2022

            Speakers

            TN

            Tianwei Ni

            Speaker · 0 followers

            BE

            Benjamin Eysenbach

            Speaker · 0 followers

            RS

            Russ Salakhutdinov

            Speaker · 13 followers

            Organizer

            I2
            I2

            ICML 2022

            Account · 493 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

            On the nonlinear correlation of ML performance across data subpopulations
            09:09

            On the nonlinear correlation of ML performance across data subpopulations

            Weixin Liang, …

            I2
            I2
            ICML 2022 3 years ago

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

            Closing remarks: Opening welcome speech: Hardware-aware efficient training (HAET)
            03:56

            Closing remarks: Opening welcome speech: Hardware-aware efficient training (HAET)

            Vahid Nia

            I2
            I2
            ICML 2022 3 years ago

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

            Data Scaling Laws in NMT: The Effect of Noise and Architecture
            05:25

            Data Scaling Laws in NMT: The Effect of Noise and Architecture

            Yamini Bansal, …

            I2
            I2
            ICML 2022 3 years ago

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

            Towards understanding how momentum improves generalization in deep learning
            04:26

            Towards understanding how momentum improves generalization in deep learning

            Samy Jelassi, …

            I2
            I2
            ICML 2022 3 years ago

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

            Learner Knowledge Levels in Adversarial ML
            03:12

            Learner Knowledge Levels in Adversarial ML

            Sophie Dai, …

            I2
            I2
            ICML 2022 3 years ago

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

            High Probability Guarantees for Nonconvex Stochastic Gradient Descent with Heavy Tails
            05:13

            High Probability Guarantees for Nonconvex Stochastic Gradient Descent with Heavy Tails

            Shaojie Li, …

            I2
            I2
            ICML 2022 3 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 2022