Next
Livestream will start soon!
Livestream has already ended.
Presentation has not been recorded yet!
  • title: SOPE: Spectrum of Off-Policy Estimators
      0:00 / 0:00
      • Report Issue
      • Settings
      • Playlists
      • Bookmarks
      • Subtitles Off
      • Playback rate
      • Quality
      • Settings
      • Debug information
      • Server sl-yoda-v3-stream-016-alpha.b-cdn.net
      • Subtitles size Medium
      • Bookmarks
      • Server
      • sl-yoda-v3-stream-016-alpha.b-cdn.net
      • sl-yoda-v3-stream-016-beta.b-cdn.net
      • 1504562137.rsc.cdn77.org
      • 1896834465.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
            SOPE: Spectrum of Off-Policy Estimators
            • Settings
            • Sync diff
            • Quality
            • Settings
            • Server
            • Quality
            • Server

            SOPE: Spectrum of Off-Policy Estimators

            Dec 6, 2021

            Speakers

            CY

            Christina Yuan

            Speaker · 0 followers

            YC

            Yash Chandak

            Speaker · 0 followers

            SG

            Stephen Giguere

            Speaker · 0 followers

            About

            Many sequential decision making problems are high-stakes and require off-policy evaluation (OPE) of a new policy using historical data collected using some other policy. One of the most common OPE technique that provides unbiased estimates is trajectory based importance sampling (IS). However, due to the high variance of trajectory IS estimates, importance sampling methods based on stationary distributions (SIS) have recently been adopted. Unfortunately, while SIS often provides lower variance e…

            Organizer

            N2
            N2

            NeurIPS 2021

            Account · 1.5k 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

            Demonstrations 4
            2:04:26

            Demonstrations 4

            N2
            N2
            NeurIPS 2021 3 years ago

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

            A versatile and efficient approach to summarize speech into utterance-level representations
            05:31

            A versatile and efficient approach to summarize speech into utterance-level representations

            João Monteiro, …

            N2
            N2
            NeurIPS 2021 3 years ago

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

            Sample-Efficient Reinforcement Learning Is Feasible for Linearly Realizable MDPs with Limited Revisiting
            15:34

            Sample-Efficient Reinforcement Learning Is Feasible for Linearly Realizable MDPs with Limited Revisiting

            Gen Li, …

            N2
            N2
            NeurIPS 2021 3 years ago

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

            On the Out-of-distribution Generalization of Probabilistic Image Modelling
            10:06

            On the Out-of-distribution Generalization of Probabilistic Image Modelling

            Mingtian Zhang, …

            N2
            N2
            NeurIPS 2021 3 years ago

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

            Wasserstein Flow Meets Replicator Dynamics: A Mean-Field Analysis of Representation Learning in Actor-Critic
            07:25

            Wasserstein Flow Meets Replicator Dynamics: A Mean-Field Analysis of Representation Learning in Actor-Critic

            Yufeng Zhang, …

            N2
            N2
            NeurIPS 2021 3 years ago

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

            Understanding End-to-End Model-Based Reinforcement Learning as Implicit Parameterization
            13:08

            Understanding End-to-End Model-Based Reinforcement Learning as Implicit Parameterization

            Clement Gehring, …

            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