Next
Livestream will start soon!
Livestream has already ended.
Presentation has not been recorded yet!
  • title: A Finite-Time Analysis of Q-Learning with Neural Network Function Approximation
      0:00 / 0:00
      • Report Issue
      • Settings
      • Playlists
      • Bookmarks
      • Subtitles Off
      • Playback rate
      • Quality
      • Settings
      • Debug information
      • Server sl-yoda-v3-stream-011-alpha.b-cdn.net
      • Subtitles size Medium
      • Bookmarks
      • Server
      • sl-yoda-v3-stream-011-alpha.b-cdn.net
      • sl-yoda-v3-stream-011-beta.b-cdn.net
      • 1150868944.rsc.cdn77.org
      • 1511650057.rsc.cdn77.org
      • Subtitles
      • Off
      • en
      • Playback rate
      • Quality
      • Subtitles size
      • Large
      • Medium
      • Small
      • Mode
      • Video Slideshow
      • Audio Slideshow
      • Slideshow
      • Video
      My playlists
        Bookmarks
          00:00:00
            A Finite-Time Analysis of Q-Learning with Neural Network Function Approximation
            • Settings
            • Sync diff
            • Quality
            • Settings
            • Server
            • Quality
            • Server

            A Finite-Time Analysis of Q-Learning with Neural Network Function Approximation

            Jul 12, 2020

            Speakers

            PX

            Pan Xu

            Speaker · 0 followers

            QG

            Quanquan Gu

            Speaker · 5 followers

            About

            Q-learning with neural network function approximation (neural Q-learning for short) is among the most prevalent deep reinforcement learning algorithms. Despite its empirical success, the non-asymptotic convergence rate of neural Q-learning remains virtually unknown. In this paper, we present a finite-time analysis of a neural Q-learning algorithm, where the data are generated from a Markov decision process and the action-value function is approximated by a deep ReLU neural network. We prove that…

            Organizer

            I2
            I2

            ICML 2020

            Account · 2.6k followers

            Categories

            Mathematics

            Category · 2.4k presentations

            AI & Data Science

            Category · 10.8k presentations

            About ICML 2020

            The International Conference on Machine Learning (ICML) is the premier gathering of professionals dedicated to the advancement of the branch of artificial intelligence known as machine learning. ICML is globally renowned for presenting and publishing cutting-edge research on all aspects of machine learning used in closely related areas like artificial intelligence, statistics and data science, as well as important application areas such as machine vision, computational biology, speech recognition, and robotics. ICML is one of the fastest growing artificial intelligence conferences in the world. Participants at ICML span a wide range of backgrounds, from academic and industrial researchers, to entrepreneurs and engineers, to graduate students and postdocs.

            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

            Poster #33

            Li Zhang

            I2
            I2
            ICML 2020 5 years ago

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

            Towards Understanding the Regularization of Adversarial Robustness on Neural Networks
            15:52

            Towards Understanding the Regularization of Adversarial Robustness on Neural Networks

            Yuxin Wen, …

            I2
            I2
            ICML 2020 5 years ago

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

            Accelerated Message Passing for Entropy-Regularized MAP Inference
            14:56

            Accelerated Message Passing for Entropy-Regularized MAP Inference

            Aldo Pacchiano, …

            I2
            I2
            ICML 2020 5 years ago

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

            Stochastic Gradient and Langevin Processes
            14:55

            Stochastic Gradient and Langevin Processes

            Xiang Cheng, …

            I2
            I2
            ICML 2020 5 years ago

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

            LowFER: Low-rank Bilinear Pooling for Link Prediction
            14:36

            LowFER: Low-rank Bilinear Pooling for Link Prediction

            Saadullah Amin, …

            I2
            I2
            ICML 2020 5 years ago

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

            Invited talk: Predicting aesthetic appreciation of images
            36:09

            Invited talk: Predicting aesthetic appreciation of images

            Naila Murray

            I2
            I2
            ICML 2020 5 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 2020