Next
Livestream will start soon!
Livestream has already ended.
Presentation has not been recorded yet!
  • title: Tactical Optimism and Pessimism for Deep Reinforcement Learning
      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
            Tactical Optimism and Pessimism for Deep Reinforcement Learning
            • Settings
            • Sync diff
            • Quality
            • Settings
            • Server
            • Quality
            • Server

            Tactical Optimism and Pessimism for Deep Reinforcement Learning

            Dec 6, 2021

            Speakers

            TM

            Ted Moskovitz

            Speaker · 0 followers

            JP

            Jack Parker-Holder

            Speaker · 1 follower

            AP

            Aldo Pacchiano

            Speaker · 0 followers

            About

            In recent years, deep off-policy actor-critic algorithms have become a dominant approach to reinforcement learning for continuous control. One of the primary drivers of this improved performance is the use of pessimistic value updates to address function approximation errors, which previously led to disappointing performance. However, a direct consequence of pessimism is reduced exploration, running counter to theoretical support for the efficacy of optimism in the face of uncertainty. So which…

            Organizer

            N2
            N2

            NeurIPS 2021

            Account · 1.9k followers

            About NeurIPS 2021

            Neural Information Processing Systems (NeurIPS) is a multi-track machine learning and computational neuroscience conference that includes invited talks, demonstrations, symposia and oral and poster presentations of refereed papers. Following the conference, there are workshops which provide a less formal setting.

            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

            Align before Fuse: Vision and Language Representation Learning with Momentum Distillation
            09:40

            Align before Fuse: Vision and Language Representation Learning with Momentum Distillation

            Junnan Li, …

            N2
            N2
            NeurIPS 2021 3 years ago

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

            Self-supervised Sun Glare Detection CNN for Self-aware Autonomous Driving
            03:01

            Self-supervised Sun Glare Detection CNN for Self-aware Autonomous Driving

            Yiqiang Chen, …

            N2
            N2
            NeurIPS 2021 3 years ago

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

            A Data-driven Markov Chain Model for COVID-19 Transmission in South Korea
            05:07

            A Data-driven Markov Chain Model for COVID-19 Transmission in South Korea

            Sujin Ahn, …

            N2
            N2
            NeurIPS 2021 3 years ago

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

            Reusing Combinatorial Structure: Faster Projections over Submodular Base Polytopes
            15:03

            Reusing Combinatorial Structure: Faster Projections over Submodular Base Polytopes

            Jai Moondra, …

            N2
            N2
            NeurIPS 2021 3 years ago

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

            Datasets for Online Controlled Experiments
            04:55

            Datasets for Online Controlled Experiments

            C. H. Bryan Liu, …

            N2
            N2
            NeurIPS 2021 3 years ago

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

            LAF | Panel discussion
            48:15

            LAF | Panel discussion

            Aaron Snoswell, …

            N2
            N2
            NeurIPS 2021 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 NeurIPS 2021