Next
Livestream will start soon!
Livestream has already ended.
Presentation has not been recorded yet!
  • title: Double Check Your State Before Trusting It: Confidence-Aware Bidirectional Offline Model-Based Imagination
      0:00 / 0:00
      • Report Issue
      • Settings
      • Playlists
      • Bookmarks
      • Subtitles Off
      • Playback rate
      • Quality
      • Settings
      • Debug information
      • Server sl-yoda-v2-stream-009-alpha.b-cdn.net
      • Subtitles size Medium
      • Bookmarks
      • Server
      • sl-yoda-v2-stream-009-alpha.b-cdn.net
      • sl-yoda-v2-stream-009-beta.b-cdn.net
      • 1766500541.rsc.cdn77.org
      • 1441886916.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
            Double Check Your State Before Trusting It: Confidence-Aware Bidirectional Offline Model-Based Imagination
            • Settings
            • Sync diff
            • Quality
            • Settings
            • Server
            • Quality
            • Server

            Double Check Your State Before Trusting It: Confidence-Aware Bidirectional Offline Model-Based Imagination

            Nov 28, 2022

            Speakers

            JL

            Jiafei Lyu

            Speaker · 0 followers

            XL

            Xiu Li

            Speaker · 0 followers

            ZL

            Zongqing Lu

            Speaker · 0 followers

            About

            The learned policy of model-free offline reinforcement learning (RL) methods is often constrained to stay within the support of datasets to avoid possible dangerous out-of-distribution actions or states, making it challenging to handle out-of-support region. Model-based RL methods offer a richer dataset and benefit generalization by generating imaginary trajectories with either trained forward or reverse dynamics model. However, the imagined transitions may be inaccurate, thus downgrading the pe…

            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

            Are You Stealing My Model? Sample Correlation for Fingerprinting Deep Neural Networks
            04:50

            Are You Stealing My Model? Sample Correlation for Fingerprinting Deep Neural Networks

            Jiyang Guan, …

            N2
            N2
            NeurIPS 2022 2 years ago

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

            CommsVAE: Learning the brain´s macroscale communication dynamics using coupled sequential  VAEs
            19:16

            CommsVAE: Learning the brain´s macroscale communication dynamics using coupled sequential VAEs

            Eloy Geenjaar, …

            N2
            N2
            NeurIPS 2022 2 years ago

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

            Lethal Dose Conjecture on Data Poisoning
            05:01

            Lethal Dose Conjecture on Data Poisoning

            Wenxiao Wang, …

            N2
            N2
            NeurIPS 2022 2 years ago

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

            BEER: Fast O(1/T) Rate for Decentralized Nonconvex Optimization with Communication Compression
            05:04

            BEER: Fast O(1/T) Rate for Decentralized Nonconvex Optimization with Communication Compression

            Haoyu Zhao, …

            N2
            N2
            NeurIPS 2022 2 years ago

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

            Adjusting the Gender Wage Gap with a Low-Dimensional Representation of Job History
            02:48

            Adjusting the Gender Wage Gap with a Low-Dimensional Representation of Job History

            Keyon Vafa, …

            N2
            N2
            NeurIPS 2022 2 years ago

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

            Scalable and Communication-Efficient Vertical Federated Learning
            22:09

            Scalable and Communication-Efficient Vertical Federated Learning

            Stacy Patterson, …

            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